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

    Neuronpedia

    INDEX
    Explanations

    dates formatted as "[day] [year]" in historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ³
    -0.74
    iquette
    -0.68
    ikuman
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.66
    ient
    -0.65
     lun
    -0.63
    çIJ
    -0.61
    wagen
    -0.60
     farming
    -0.59
     plantation
    -0.59
    POSITIVE LOGITS
    ...]
    1.52
    âĢ¦]
    1.47
    Pg
    1.24
    ?]
    1.08
    Footnote
    1.06
    emphasis
    1.00
    REDACTED
    0.98
    sic
    0.96
    !]
    0.94
     ].
    0.92
    Act Density 0.030%

    No Known Activations