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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.09
    4:0.09
    5:0.08
    6:0.07
    7:0.07
    8:0.08
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
    eger
    -1.75
    xx
    -1.74
    ppel
    -1.69
    neutral
    -1.63
    uner
    -1.60
    eligible
    -1.53
    xt
    -1.52
     Availability
    -1.49
    received
    -1.49
     nickname
    -1.48
    POSITIVE LOGITS
    Unity
    1.67
     comrades
    1.64
     creative
    1.62
    ��
    1.59
     strugg
    1.57
     folks
    1.57
     Eleanor
    1.56
    Georgia
    1.55
     fraternity
    1.53
     brethren
    1.53
    Act Density 0.000%

    No Known Activations