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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of places

    oai_token-act-pair · gpt-3.5-turbo

    references to actions and events in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orld
    -0.85
     emergencies
    -0.84
    terday
    -0.74
     Gon
    -0.71
     apocalypse
    -0.71
     mars
    -0.70
    ylum
    -0.69
    eday
    -0.66
     enthusi
    -0.65
    Job
    -0.65
    POSITIVE LOGITS
    dfx
    0.86
     Cosponsors
    0.82
    ãĥĩãĤ£
    0.79
     Rubber
    0.78
    px
    0.76
    rued
    0.76
    ilic
    0.73
    Ã
    0.71
    uscript
    0.70
    ãĥ¼ãĥ
    0.69
    Act Density 0.251%

    No Known Activations