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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals and their professional roles or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĩ
    -0.15
    aylor
    -0.15
    (es
    -0.14
    iyan
    -0.13
    .tap
    -0.13
     Pole
    -0.13
     Ens
    -0.13
    _ED
    -0.13
    å¹³æĪIJ
    -0.13
    ìĦŃ
    -0.13
    POSITIVE LOGITS
     spokesman
    0.28
     spokeswoman
    0.22
     spokesperson
    0.20
     who
    0.20
     professor
    0.19
     spokes
    0.19
     research
    0.17
     director
    0.16
     speaking
    0.16
     author
    0.15
    Act Density 0.124%

    No Known Activations