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

    Neuronpedia

    INDEX
    Explanations

    sentences conveying negative news or unfavorable outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.22
    1:0.09
    2:0.04
    3:0.06
    4:0.04
    5:0.07
    6:0.03
    7:0.02
    8:0.22
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
    govtrack
    -2.16
     coerc
    -2.02
     ga
    -1.88
    adobe
    -1.87
    xual
    -1.80
     RELEASE
    -1.74
    usc
    -1.72
     Amit
    -1.71
     ascending
    -1.69
     coh
    -1.68
    POSITIVE LOGITS
    iev
    1.80
    Secondly
    1.78
     Roses
    1.71
    ry
    1.70
    essim
    1.68
    ruce
    1.67
    abor
    1.67
    remlin
    1.64
    rors
    1.60
    esters
    1.59
    Act Density 0.000%

    No Known Activations