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

    Neuronpedia

    INDEX
    Explanations

    formal mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.05
    2:0.09
    3:0.08
    4:0.09
    5:0.08
    6:0.07
    7:0.09
    8:0.07
    9:0.08
    10:0.09
    11:0.09
    Negative Logits
    �
    -1.83
     Agenda
    -1.68
     Constantine
    -1.60
     Doomsday
    -1.53
    utsu
    -1.53
    黒
    -1.48
     WARN
    -1.44
    redo
    -1.44
    Beat
    -1.42
     agenda
    -1.41
    POSITIVE LOGITS
    eredith
    2.06
    umably
    1.99
    ividual
    1.82
    andestine
    1.73
     Mellon
    1.67
    reau
    1.67
    ibrary
    1.61
    burse
    1.59
    htaking
    1.57
    -[
    1.56
    Act Density 0.000%

    No Known Activations