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

    Neuronpedia

    INDEX
    Explanations

    expressions related to visual perception

    oai_token-act-pair · gpt-3.5-turbo

    instances of perception verbs related to seeing or observing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hero
    -0.69
     Chev
    -0.61
     Miko
    -0.60
     Dism
    -0.60
    aston
    -0.59
    reply
    -0.59
    gart
    -0.59
    agraph
    -0.58
     flood
    -0.58
     resur
    -0.57
    POSITIVE LOGITS
    ãĤ´
    0.75
     entails
    0.73
     Learned
    0.67
    Ca
    0.67
     unfolding
    0.66
    ALD
    0.65
    UFC
    0.64
    ulse
    0.64
    atel
    0.64
    ulin
    0.64
    Act Density 0.240%

    No Known Activations