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

    Neuronpedia

    INDEX
    Explanations

    references to social dynamics and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    daemon
    -0.18
     Kro
    -0.15
    tsky
    -0.15
    chts
    -0.15
    wap
    -0.15
    engo
    -0.14
    ssue
    -0.14
    -gnu
    -0.14
    _station
    -0.14
    åħį
    -0.14
    POSITIVE LOGITS
     instead
    0.23
     now
    0.22
    instead
    0.22
     artık
    0.21
     Gone
    0.18
     ÑĤепеÑĢÑĮ
    0.18
     Instead
    0.18
     increased
    0.17
     niż
    0.17
    Instead
    0.17
    Act Density 0.221%

    No Known Activations