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

    Neuronpedia

    INDEX
    Explanations

    special characters and unusual symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geries
    -1.03
     foreground
    -0.82
     distracted
    -0.80
     distracting
    -0.78
     intrig
    -0.70
    xus
    -0.68
     dividing
    -0.68
     offending
    -0.68
     ordinary
    -0.67
    gery
    -0.66
    POSITIVE LOGITS
    и
    1.09
    о
    0.96
    Ħ
    0.96
    æѦ
    0.93
    ר
    0.93
    ski
    0.91
    ij
    0.91
    Ñĥ
    0.91
    ļ
    0.90
    ł
    0.89
    Act Density 0.005%

    No Known Activations