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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-control and personal struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.77
    IsMutable
    -0.71
    SequentialGroup
    -0.69
    KommentareTeilen
    -0.68
     שוליים
    -0.68
     ExecuteAsync
    -0.66
    aarrggbb
    -0.62
     Monfieur
    -0.59
     كومونز
    -0.58
    Heard
    -0.58
    POSITIVE LOGITS
     involunt
    0.72
     compulsion
    0.67
     involuntarily
    0.67
     compelled
    0.64
     instinct
    0.63
     unavoidable
    0.61
     impulse
    0.61
     compulsive
    0.60
     irresistible
    0.60
     involuntary
    0.60
    Act Density 0.265%

    No Known Activations