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

    Neuronpedia

    INDEX
    Explanations

    behaviors related to social interactions and the notion of acting in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Easily
    -0.19
     easily
    -0.17
    æĹı
    -0.14
    [NUM
    -0.13
    accur
    -0.13
    accuracy
    -0.13
    aset
    -0.13
    etak
    -0.13
    ãĥ¥
    -0.13
     easiest
    -0.13
    POSITIVE LOGITS
    aul
    0.28
    uate
    0.28
     like
    0.27
    /react
    0.26
     upon
    0.25
    ully
    0.24
    uated
    0.21
     liked
    0.21
     contrary
    0.20
    /respond
    0.20
    Act Density 0.041%

    No Known Activations