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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to identity and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.08
    3:0.07
    4:0.15
    5:0.03
    6:0.31
    7:0.08
    8:0.03
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    ruary
    -1.84
    escription
    -1.45
    artney
    -1.44
    algia
    -1.39
    esides
    -1.33
    ificantly
    -1.30
     サ
    -1.28
     warr
    -1.26
    asionally
    -1.25
    cius
    -1.21
    POSITIVE LOGITS
    stones
    1.41
     conce
    1.34
    aign
    1.32
    holes
    1.31
    bour
    1.26
     horizon
    1.23
    spring
    1.20
     Founding
    1.18
    hole
    1.17
    bull
    1.17
    Act Density 0.005%

    No Known Activations