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

    Neuronpedia

    INDEX
    Explanations

    adverbs and adverbial phrases indicating likelihood or frequency

    oai_token-act-pair · gpt-3.5-turbo

    words indicating probabilities or frequencies of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.88
    galitarian
    -0.74
    amins
    -0.73
    ukong
    -0.71
    perture
    -0.70
    aez
    -0.69
    ircraft
    -0.69
    oir
    -0.68
    ibles
    -0.68
    sein
    -0.67
    POSITIVE LOGITS
     culminating
    1.19
     resulting
    1.17
     indicating
    1.16
     involving
    1.13
     intending
    1.11
     implying
    1.10
     relying
    1.09
     citing
    1.09
     preferring
    1.08
     numbering
    1.07
    Act Density 0.127%

    No Known Activations