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

    Neuronpedia

    INDEX
    Explanations

    words indicating exclusivity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    NOW
    -3.08
    apest
    -2.92
    ancies
    -2.87
    ��
    -2.76
    eve
    -2.66
    ANC
    -2.65
    iculty
    -2.60
     Zh
    -2.60
     Houses
    -2.59
     Achievements
    -2.58
    POSITIVE LOGITS
     voic
    3.44
     tro
    3.01
     locker
    2.83
     lawy
    2.82
     offic
    2.78
     gag
    2.76
     dial
    2.72
     clos
    2.68
     filler
    2.66
     bullpen
    2.62
    Act Density 0.000%

    No Known Activations