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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.09
    4:0.07
    5:0.07
    6:0.08
    7:0.08
    8:0.09
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
    ghazi
    -3.62
    anooga
    -3.45
    icago
    -3.25
    �
    -3.02
    isSpecialOrderable
    -2.81
    hattan
    -2.77
    noxious
    -2.75
    anamo
    -2.66
    bnb
    -2.59
    achusetts
    -2.59
    POSITIVE LOGITS
     newsletters
    2.71
     Expression
    2.46
     Donation
    2.43
    Dialogue
    2.40
     kilometres
    2.35
     Lon
    2.33
     composition
    2.33
     Ole
    2.32
     Gene
    2.31
     formula
    2.31
    Act Density 0.000%

    No Known Activations