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

    Neuronpedia

    INDEX
    Explanations

    references to political issues and social justice themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gerald
    -0.64
    cause
    -0.63
    unless
    -0.58
    Spoiler
    -0.56
    Published
    -0.56
    .,"
    -0.56
    Picture
    -0.55
     TheNitromeFan
    -0.55
    rex
    -0.55
     Graves
    -0.55
    POSITIVE LOGITS
     alike
    1.10
     thereof
    1.10
     thereafter
    1.02
     thereto
    0.98
     therein
    0.87
     respectively
    0.84
     afterwards
    0.77
     ensuing
    0.77
     afterward
    0.72
    )?
    0.70
    Act Density 0.537%

    No Known Activations