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

    Neuronpedia

    INDEX
    Explanations

    names and references to identity of individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to names and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.81
    productive
    -0.78
     ACTIONS
    -0.76
    ractical
    -0.74
    forums
    -0.73
    atform
    -0.73
    nw
    -0.72
    requires
    -0.72
    Progress
    -0.71
     stalls
    -0.71
    POSITIVE LOGITS
     redacted
    1.14
     engraved
    1.04
     tattoo
    0.88
     initials
    0.87
     etched
    0.87
     blurred
    0.87
     typo
    0.86
     surname
    0.84
     dece
    0.84
     synonymous
    0.82
    Act Density 0.382%

    No Known Activations