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

    Neuronpedia

    INDEX
    Explanations

    references to people, particularly second-person ("you") and first-person ("me") pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perfons
    -0.61
     Cæsar
    -0.61
     itſelf
    -0.58
     himſelf
    -0.57
     quæ
    -0.56
     myſelf
    -0.56
     Sahel
    -0.55
    نما
    -0.54
    Cyfarwyddwr
    -0.54
     Josephus
    -0.53
    POSITIVE LOGITS
     a
    0.86
    DockStyle
    0.86
    ScopeManager
    0.78
    Gimme
    0.74
     the
    0.74
    mutable
    0.74
    CGRectMake
    0.74
    Gön
    0.73
     an
    0.71
    ]>=
    0.70
    Act Density 0.120%

    No Known Activations