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

    Neuronpedia

    INDEX
    Explanations

    sentences that start with a period or contain punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.35
    3:0.05
    4:0.06
    5:0.04
    6:0.13
    7:0.04
    8:0.06
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
     levers
    -1.76
     corridors
    -1.68
    arettes
    -1.65
     streams
    -1.63
     presentations
    -1.61
     channels
    -1.59
    nels
    -1.59
     shenanigans
    -1.54
    nesses
    -1.53
    sheets
    -1.51
    POSITIVE LOGITS
    llah
    1.67
    dfx
    1.63
    ía
    1.59
    ë
    1.56
    Quantity
    1.53
    feld
    1.52
    KNOWN
    1.50
    ENA
    1.43
     liv
    1.41
    的
    1.41
    Act Density 0.006%

    No Known Activations