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

    Neuronpedia

    INDEX
    Explanations

    questions seeking personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.10
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.07
    8:0.07
    9:0.09
    10:0.07
    11:0.07
    Negative Logits
    icago
    -2.81
    outheast
    -2.67
    San
    -2.66
    eca
    -2.65
    cffffcc
    -2.62
    EGIN
    -2.52
    employment
    -2.52
     sanctuary
    -2.51
    ��
    -2.51
    atto
    -2.44
    POSITIVE LOGITS
     Myst
    3.04
     Gly
    2.83
     Wyr
    2.82
     Glac
    2.79
     Pry
    2.73
     Pinball
    2.71
     Manip
    2.70
     MOT
    2.69
     Eternity
    2.62
     Wiz
    2.61
    Act Density 0.000%

    No Known Activations