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

    Neuronpedia

    INDEX
    Explanations

    specific formatting cues or structure indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dynamic
    -0.74
    ="../../
    -0.73
     Schroeder
    -0.70
    oted
    -0.67
    ggen
    -0.67
    etsk
    -0.67
    ../../../
    -0.66
    Hos
    -0.66
     Schröder
    -0.66
     Hos
    -0.65
    POSITIVE LOGITS
     AIT
    0.96
     EIF
    0.94
     Iain
    0.93
    PMailer
    0.93
     AIP
    0.91
     Eis
    0.90
     DAI
    0.90
    Cair
    0.88
    EIS
    0.88
     Reine
    0.85
    Act Density 0.331%

    No Known Activations