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

    Neuronpedia

    INDEX
    Explanations

    non-English characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     demos
    -0.87
     factions
    -0.74
     neighb
    -0.74
     unpop
    -0.74
     challeng
    -0.73
     grips
    -0.73
     blacklist
    -0.71
     wrinkles
    -0.71
    okin
    -0.71
     piracy
    -0.70
    POSITIVE LOGITS
    à¥
    2.14
    à¤
    2.14
    ा
    1.98
     à¤
    1.78
    ×Ļ×
    1.49
    ×Ķ
    1.46
    ×ķ
    1.46
    ×
    1.43
    ר
    1.41
    ×Ļ
    1.39
    Act Density 0.007%

    No Known Activations