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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a cause-and-effect relationship

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causes and effects or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.67
    ategories
    -0.63
    anchester
    -0.60
    tty
    -0.57
    ounding
    -0.56
    ufact
    -0.56
     kindred
    -0.55
    essen
    -0.55
     Week
    -0.55
    jab
    -0.54
    POSITIVE LOGITS
     thereafter
    0.87
     onwards
    0.80
     they
    0.79
     there
    0.79
     nobody
    0.74
     THERE
    0.72
    forth
    0.71
     thereof
    0.71
     we
    0.69
     it
    0.68
    Act Density 0.259%

    No Known Activations