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

    Neuronpedia

    INDEX
    Explanations

    complexities and contradictions in narratives or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.05
    2:0.01
    3:0.09
    4:0.06
    5:0.06
    6:0.07
    7:0.02
    8:0.40
    9:0.08
    10:0.03
    11:0.03
    Negative Logits
    ldom
    -2.28
    eday
    -2.23
    ouble
    -2.19
    etheless
    -2.17
    alions
    -2.08
    aths
    -2.06
    gemony
    -1.88
    idth
    -1.84
    ��
    -1.84
    iden
    -1.83
    POSITIVE LOGITS
    iHUD
    1.80
    shock
    1.71
     Omaha
    1.69
       
    1.69
    HUD
    1.61
     hay
    1.61
     FX
    1.60
    eering
    1.57
    electric
    1.54
    Shock
    1.53
    Act Density 0.001%

    No Known Activations