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

    Neuronpedia

    INDEX
    Explanations

    references to artificial intelligence and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovies
    -0.18
    airro
    -0.16
    arness
    -0.15
    BED
    -0.15
    arser
    -0.15
    storybook
    -0.15
    axe
    -0.14
    á»IJ
    -0.14
    _Header
    -0.14
     uintptr
    -0.14
    POSITIVE LOGITS
     intelligence
    0.44
     Intelligence
    0.40
    intelligence
    0.34
     intelig
    0.31
    elligence
    0.30
     intellig
    0.29
    -int
    0.28
     intelligent
    0.26
     neural
    0.26
     intel
    0.25
    Act Density 0.013%

    No Known Activations