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

    Neuronpedia

    INDEX
    Explanations

    references to actions involving physical movement or interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.92
    WireFormatLite
    -0.63
    contentLoaded
    -0.59
     agrí
    -0.57
    ⓘ
    -0.55
     Италијани
    -0.55
     względu
    -0.55
    initas
    -0.54
     ویکی‌پدی
    -0.54
     otomatig
    -0.54
    POSITIVE LOGITS
     closer
    0.69
     downstairs
    0.67
     towards
    0.66
     upstairs
    0.66
     forward
    0.64
     toward
    0.62
     inside
    0.60
     <<<<<<<<<<<<<<
    0.59
     corriendo
    0.56
     running
    0.54
    Act Density 0.209%

    No Known Activations