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

    Neuronpedia

    INDEX
    Explanations

    the preposition "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.09
    3:0.09
    4:0.09
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     Sear
    -1.97
     Submission
    -1.81
     CLICK
    -1.77
     Activ
    -1.71
    ...]
    -1.63
     Keeper
    -1.63
    EStreamFrame
    -1.60
    Writ
    -1.58
     GOODMAN
    -1.57
     Please
    -1.55
    POSITIVE LOGITS
    onite
    1.94
    lot
    1.77
    EF
    1.74
    notations
    1.64
    ンジ
    1.59
     contrast
    1.55
    AIN
    1.54
     adjective
    1.54
     bitterness
    1.54
    lly
    1.52
    Act Density 0.000%

    No Known Activations