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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements attributed to individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements or reports made by individuals in a discussion or event context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PAC
    -0.67
    psy
    -0.66
    Subject
    -0.63
     asses
    -0.62
    Kin
    -0.61
    ERC
    -0.59
    Higher
    -0.59
    docs
    -0.59
    RO
    -0.58
    DATA
    -0.58
    POSITIVE LOGITS
    ogun
    0.96
     QC
    0.83
    veland
    0.80
    tsky
    0.80
    aley
    0.79
    verett
    0.75
    hement
    0.71
     stern
    0.71
    ombat
    0.68
    ÄŁ
    0.67
    Act Density 0.461%

    No Known Activations