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

    Neuronpedia

    INDEX
    Explanations

    phrases containing non-English characters

    oai_token-act-pair · gpt-3.5-turbo

    Arabic characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cly
    -0.76
     NX
    -0.76
     wallets
    -0.75
    erest
    -0.74
     pensions
    -0.73
     demos
    -0.73
     whistlebl
    -0.72
     supervisors
    -0.71
     tether
    -0.71
     licens
    -0.71
    POSITIVE LOGITS
    ا
    2.40
    ÙĪ
    2.37
    Û
    2.36
    د
    2.34
    Ù
    2.31
    ت
    2.30
    ر
    2.30
    Ùĩ
    2.29
    Ùħ
    2.28
    اØ
    2.26
    Act Density 0.008%

    No Known Activations