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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or expressions of disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollapsed
    -0.15
    erna
    -0.15
    nte
    -0.14
    Ã¤ÃŁ
    -0.14
    emean
    -0.13
    nty
    -0.13
    eca
    -0.13
    .pm
    -0.13
    ackages
    -0.13
    ingt
    -0.13
    POSITIVE LOGITS
    ably
    0.19
    -looking
    0.16
    oron
    0.16
    prak
    0.15
    ¿
    0.14
    997
    0.14
    oles
    0.14
    iteral
    0.14
    yl
    0.14
    isex
    0.14
    Act Density 0.018%

    No Known Activations