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

    Neuronpedia

    INDEX
    Explanations

    the word "mostly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.08
    3:0.08
    4:0.09
    5:0.08
    6:0.09
    7:0.08
    8:0.09
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
    uces
    -1.61
     modelling
    -1.56
     hatch
    -1.53
     recomm
    -1.47
     unloaded
    -1.46
     reassured
    -1.45
     withdrawn
    -1.45
     refreshed
    -1.45
     HOT
    -1.44
    itiz
    -1.43
    POSITIVE LOGITS
    ��
    1.73
     Parables
    1.71
    qqa
    1.60
     Scenes
    1.56
    ardo
    1.54
    imation
    1.54
    yssey
    1.52
     func
    1.52
    の魔
    1.51
    ategories
    1.46
    Act Density 0.000%

    No Known Activations