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

    Neuronpedia

    INDEX
    Explanations

    specific historical or time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to early events or historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    md
    -0.85
    pherd
    -0.79
    agree
    -0.74
    Pool
    -0.72
    lua
    -0.71
    unal
    -0.69
    bnb
    -0.68
    arse
    -0.67
    Msg
    -0.66
    ractor
    -0.66
    POSITIVE LOGITS
     iterations
    1.14
     stages
    1.13
     adop
    1.10
     incarnation
    1.06
     drafts
    1.04
     phases
    1.04
     beginnings
    1.03
     incarn
    1.02
     generations
    1.01
     versions
    1.01
    Act Density 0.083%

    No Known Activations