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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    capitalized proper nouns and specific character names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSpecialOrderable
    -0.67
     Gree
    -0.66
    ancies
    -0.66
    changed
    -0.65
    cause
    -0.65
    properties
    -0.63
    fires
    -0.62
    minded
    -0.62
     Dru
    -0.62
    cation
    -0.61
    POSITIVE LOGITS
     guiActiveUn
    1.05
     et
    0.77
    EStreamFrame
    0.75
     ÃĹ
    0.73
     Productions
    0.72
     Goes
    0.71
     partName
    0.68
    âĦ¢:
    0.68
     Presents
    0.68
     guiName
    0.67
    Act Density 0.236%

    No Known Activations