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

    Neuronpedia

    INDEX
    Explanations

    sentiments indicating detachment from reality or understanding of societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endphp
    -0.45
     bluzka
    -0.45
     ""],
    -0.43
     sukienka
    -0.41
     wikipagina
    -0.40
     TimeUnit
    -0.40
     zboží
    -0.40
    Карьера
    -0.36
    Manbalar
    -0.36
     produktu
    -0.36
    POSITIVE LOGITS
    GEBURTSDATUM
    0.52
     surla
    0.49
    ReusableCell
    0.48
     ModelExpression
    0.47
    __(/*!
    0.44
     ProtoMessage
    0.43
     ignorance
    0.43
     noDo
    0.42
    lichung
    0.42
    EndContext
    0.41
    Act Density 0.476%

    No Known Activations