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

    Neuronpedia

    INDEX
    Explanations

    relative clauses with "which" and percentages

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and frequently occurring phrases within statistics or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.79
    é»Ĵ
    -0.77
    dayName
    -0.69
    SpaceEngineers
    -0.69
    Interstitial
    -0.63
    Synopsis
    -0.61
    argo
    -0.61
    isin
    -0.60
    pire
    -0.60
    ãĥīãĥ©
    -0.60
    POSITIVE LOGITS
     41
    1.20
     34
    1.19
     22
    1.18
     14
    1.18
     28
    1.17
     40
    1.17
     44
    1.17
     42
    1.16
     68
    1.16
     33
    1.15
    Act Density 0.243%

    No Known Activations