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

    Neuronpedia

    INDEX
    Explanations

    vertical bars symbol "|" and lowercase letters "l" in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    sections of text with a focus on formatting and structure markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chenko
    -0.74
    anium
    -0.73
    ibly
    -0.72
    atem
    -0.71
    opian
    -0.70
    esi
    -0.69
    amen
    -0.68
    aband
    -0.68
    ory
    -0.67
    ixel
    -0.67
    POSITIVE LOGITS
    cffff
    1.01
     |--
    0.86
    ··
    0.83
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.82
    ————————
    0.81
     CrossRef
    0.81
     Contents
    0.80
     Difference
    0.78
    ¯¯¯¯¯¯¯¯
    0.78
    \\\\\\\\\\\\\\\\
    0.77
    Act Density 0.028%

    No Known Activations