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

    Neuronpedia

    INDEX
    Explanations

    references to negative emotions and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.71
     Vit
    -0.69
     onData
    -0.68
     تضيفلها
    -0.67
    ([...
    -0.63
    tocin
    -0.61
    ึ้น
    -0.61
    éndole
    -0.60
    anmoins
    -0.60
    ÍST
    -0.59
    POSITIVE LOGITS
     negative
    1.46
     Negative
    1.42
    NEGATIVE
    1.40
     negatives
    1.36
    negative
    1.34
     (-)
    1.31
    Negative
    1.29
     negativity
    1.28
     NEGATIVE
    1.25
     negatively
    1.21
    Act Density 0.326%

    No Known Activations