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

    Neuronpedia

    INDEX
    Explanations

    statements introducing lists of items or explanations

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that introduce lists or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.91
     tremend
    -0.82
    ĸļ
    -0.78
    izons
    -0.74
    oud
    -0.73
    dinand
    -0.71
    etooth
    -0.70
    ridor
    -0.70
    oes
    -0.70
    ikuman
    -0.69
    POSITIVE LOGITS
     Provided
    0.91
     namely
    0.84
     "âĢ¦
    0.83
    ³³³³³³³³³³³³³³³³
    0.79
    YES
    0.78
    $$$$
    0.77
     Logged
    0.77
     http
    0.76
     They
    0.75
     Whereas
    0.75
    Act Density 0.270%

    No Known Activations