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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.19
    2:0.06
    3:0.06
    4:0.05
    5:0.16
    6:0.10
    7:0.04
    8:0.08
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
     accidents
    -1.67
    idan
    -1.64
    ila
    -1.54
    anship
    -1.52
     shelters
    -1.52
     stress
    -1.51
    urden
    -1.49
    abor
    -1.48
     licences
    -1.46
     pressures
    -1.46
    POSITIVE LOGITS
    �
    2.02
    ْ
    1.89
    Pixel
    1.87
    (\
    1.83
    toc
    1.80
     Rove
    1.69
    @
    1.65
    Buy
    1.64
    (_
    1.63
     Icar
    1.61
    Act Density 0.001%

    No Known Activations