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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or their possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.13
    3:0.03
    4:0.06
    5:0.08
    6:0.13
    7:0.02
    8:0.19
    9:0.06
    10:0.08
    11:0.08
    Negative Logits
    andise
    -1.42
    tty
    -1.37
    nz
    -1.35
     CLS
    -1.33
    nect
    -1.29
     partName
    -1.29
    atform
    -1.25
    upp
    -1.25
    ivation
    -1.22
     Suz
    -1.22
    POSITIVE LOGITS
     alike
    1.49
    senal
    1.35
     cousins
    1.30
     neighboring
    1.28
     cousin
    1.26
    "},"
    1.26
    ESCO
    1.25
    ée
    1.23
     abuser
    1.23
     predecessor
    1.22
    Act Density 0.014%

    No Known Activations