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

    Neuronpedia

    INDEX
    Explanations

    references to pubs or pubs-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pubs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FUL
    -0.82
    IRD
    -0.79
    OHN
    -0.78
    llor
    -0.76
     EFF
    -0.73
     Gaia
    -0.72
    xual
    -0.71
     GOODMAN
    -0.70
     Isles
    -0.68
    ylum
    -0.66
    POSITIVE LOGITS
    lique
    1.40
    lisher
    1.38
    lishing
    1.37
    lishes
    1.36
    lish
    1.35
    escent
    1.22
    lik
    1.08
    bing
    1.06
    bed
    0.97
    keys
    0.90
    Act Density 0.015%

    No Known Activations