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

    Neuronpedia

    INDEX
    Explanations

    words related to something that is expected or planned to happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    mentions of upcoming events or releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    educ
    -0.71
    spe
    -0.70
    yer
    -0.69
    elo
    -0.69
    umbledore
    -0.68
    verbs
    -0.68
    midt
    -0.67
    ocker
    -0.66
    WA
    -0.66
    aples
    -0.65
    POSITIVE LOGITS
     forthcoming
    1.10
     disclosures
    0.81
     RELE
    0.74
     Parenthood
    0.72
    forth
    0.72
     antioxid
    0.71
    ĸļ
    0.70
    urnal
    0.69
     undone
    0.69
     deliveries
    0.68
    Act Density 0.006%

    No Known Activations