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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal or regulatory actions and their consequences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    saraba
    -0.60
     ExecuteAsync
    -0.54
    kloped
    -0.47
    Życiorys
    -0.46
    matchCondition
    -0.45
    นวน
    -0.45
    TestBed
    -0.44
     Interface
    -0.44
    '][$
    -0.43
    ://$
    -0.43
    POSITIVE LOGITS
    ArrowToggle
    0.71
    DOCTYPE
    0.61
    ddots
    0.58
    SequentialGroup
    0.56
     permissive
    0.56
     reckless
    0.55
    Bindable
    0.55
     carelessness
    0.55
    //
    0.52
     liberties
    0.52
    Act Density 0.269%

    No Known Activations