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

    Neuronpedia

    INDEX
    Explanations

    emotional and thought-provoking language related to feelings and consciousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.75
     henvisninger
    -0.63
    Jereo
    -0.57
    出版年
    -0.57
     orar
    -0.56
     ModelExpression
    -0.56
     صوتيه
    -0.54
    LayoutStyle
    -0.52
     Numerade
    -0.52
    enumii
    -0.51
    POSITIVE LOGITS
     inducing
    0.69
    rifying
    0.63
     provoking
    0.62
    isome
    0.59
     shattering
    0.58
    inducing
    0.58
    provoking
    0.56
    BREAKING
    0.55
     wrecking
    0.55
    evo
    0.55
    Act Density 0.363%

    No Known Activations