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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity or possession

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person's name or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    س
    -0.74
    INO
    -0.74
    à¼
    -0.73
    itect
    -0.70
    ipation
    -0.69
    itud
    -0.68
     Sakuya
    -0.67
    wav
    -0.67
     TRANS
    -0.66
    1080
    -0.65
    POSITIVE LOGITS
    anmar
    1.28
    stery
    1.25
    self
    1.21
    ths
    1.13
    riad
    1.09
    selves
    1.07
     own
    1.00
     apologies
    0.95
     Own
    0.88
    stic
    0.87
    Act Density 0.033%

    No Known Activations