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

    Neuronpedia

    INDEX
    Explanations

    sentences or statements indicating certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express conclusions or statements of fact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.95
     gobl
    -0.85
     challeng
    -0.81
     preval
    -0.77
     horrend
    -0.76
     unsus
    -0.76
     satell
    -0.72
     defe
    -0.69
     millenn
    -0.69
     princ
    -0.69
    POSITIVE LOGITS
     He
    1.50
     "[
    1.44
     Asked
    1.37
     Speaking
    1.36
     "(
    1.36
     "
    1.30
     However
    1.24
     Specifically
    1.23
     "...
    1.19
     "'
    1.18
    Act Density 0.320%

    No Known Activations