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

    Neuronpedia

    INDEX
    Explanations

    mentions of segments and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Conroy
    -0.99
     Kes
    -0.97
     Lili
    -0.95
    Lili
    -0.92
    Kes
    -0.91
     Vog
    -0.84
    parsedMessage
    -0.83
     vog
    -0.82
    полнитель
    -0.82
     Forman
    -0.82
    POSITIVE LOGITS
    {{
    0.84
     Wendell
    0.82
    ="{{
    0.80
     Dewey
    0.80
    一个
    0.77
     Fras
    0.75
     kefir
    0.74
    CAPTCHA
    0.73
    windigkeit
    0.73
    Marcia
    0.73
    Act Density 0.263%

    No Known Activations