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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical contact or gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.15
     boca
    -0.15
    coil
    -0.15
    cgi
    -0.15
     AppModule
    -0.15
    زب
    -0.14
    wer
    -0.14
    WER
    -0.14
    .builders
    -0.14
    amburg
    -0.14
    POSITIVE LOGITS
     away
    0.34
     off
    0.22
     Away
    0.22
     up
    0.21
     out
    0.21
     into
    0.21
     down
    0.20
    Away
    0.20
     handful
    0.18
     apart
    0.17
    Act Density 0.140%

    No Known Activations