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

    Neuronpedia

    INDEX
    Explanations

    specific items or locations mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    language referring to specific attributes or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVERS
    -0.96
    ults
    -0.83
    udi
    -0.83
    acers
    -0.76
    birds
    -0.75
    docs
    -0.74
    masters
    -0.73
    ãĥ¼ãĤ¯
    -0.73
    abies
    -0.72
    iddles
    -0.72
    POSITIVE LOGITS
     amount
    1.32
     number
    1.09
     subset
    1.04
     predetermined
    1.03
     percentage
    1.01
     location
    1.00
     quantity
    0.99
     degree
    0.93
     piece
    0.91
     destination
    0.91
    Act Density 0.097%

    No Known Activations