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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.04
    3:0.06
    4:0.05
    5:0.02
    6:0.28
    7:0.28
    8:0.04
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
    onomous
    -1.41
     horizont
    -1.41
    uably
    -1.39
    dates
    -1.39
    ��
    -1.38
    LOS
    -1.36
     liaison
    -1.34
    milo
    -1.32
    oplan
    -1.31
     tert
    -1.31
    POSITIVE LOGITS
     Mim
    1.68
     Malt
    1.44
     clip
    1.44
     recess
    1.44
     Hide
    1.39
    >)
    1.38
     Hats
    1.36
    ught
    1.34
     Fault
    1.33
    });
    1.33
    Act Density 0.001%

    No Known Activations