Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of names related to Russia or words with 'Russian' sound in them

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.81
    holders
    -0.73
    ¿½
    -0.68
     Sinclair
    -0.67
     vested
    -0.63
     unseen
    -0.61
     harbour
    -0.61
     conspicuous
    -0.60
    opsy
    -0.59
     faults
    -0.59
    POSITIVE LOGITS
    byss
    1.14
    kies
    1.14
    sel
    1.09
    coe
    1.00
    hes
    0.97
    ques
    0.97
    kin
    0.96
    sels
    0.95
    sell
    0.92
    chem
    0.91
    Act Density 0.017%

    No Known Activations