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

    Neuronpedia

    INDEX
    Explanations

    links or options displayed in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    vertical bars and similar symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chenko
    -0.77
    anium
    -0.71
    ory
    -0.71
    anski
    -0.70
    ixel
    -0.70
    alis
    -0.70
    amen
    -0.69
    ibly
    -0.69
    stellar
    -0.68
    aband
    -0.68
    POSITIVE LOGITS
    cffff
    1.00
     |--
    0.87
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.86
    ¯¯¯¯¯¯¯¯
    0.84
    ··
    0.81
     CrossRef
    0.80
    ————————
    0.79
    \\\\\\\\\\\\\\\\
    0.77
     grep
    0.77
     Difference
    0.75
    Act Density 0.022%

    No Known Activations