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

    Neuronpedia

    INDEX
    Explanations

    words associated with immediate actions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forhold
    -0.45
    󠁿
    -0.44
     løpet
    -0.43
    enumi
    -0.42
     desses
    -0.41
     africains
    -0.41
    espoir
    -0.40
    DispatchToProps
    -0.40
     acrí
    -0.40
    WriteLiteral
    -0.40
    POSITIVE LOGITS
     immediately
    1.58
    immediately
    1.48
     Immediately
    1.48
    Immediately
    1.48
     immediate
    1.41
    Immediate
    1.37
     Immediate
    1.36
    immediate
    1.36
     immedi
    1.26
     instantly
    1.26
    Act Density 0.182%

    No Known Activations