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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to rankings or performance comparisons

    oai_token-act-pair · gpt-3.5-turbo

    statistical comparisons and superlatives indicating extremes or significant values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    din
    -0.70
    fen
    -0.68
    opard
    -0.68
    blers
    -0.67
    dot
    -0.66
    docs
    -0.65
    oras
    -0.64
     Idol
    -0.64
    hops
    -0.64
    raf
    -0.63
    POSITIVE LOGITS
    ever
    1.02
     consecutive
    0.86
     ever
    0.85
     occurrence
    0.81
     cumulative
    0.81
     omission
    0.79
     outburst
    0.77
     haul
    0.77
     reversal
    0.76
     outing
    0.76
    Act Density 0.134%

    No Known Activations