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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating a sense of importance or significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.11
    3:0.12
    4:0.28
    5:0.05
    6:0.07
    7:0.15
    8:0.02
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
     rounding
    -1.43
    ranging
    -1.40
     unbeliev
    -1.39
     tampering
    -1.36
     millenn
    -1.34
     naming
    -1.29
    UNCH
    -1.28
     unveiling
    -1.28
     disappearance
    -1.27
    dding
    -1.27
    POSITIVE LOGITS
     oneself
    1.64
     alive
    1.49
     entails
    1.42
     accountable
    1.42
    rine
    1.39
     commandments
    1.38
     yourself
    1.32
     sacred
    1.30
    itors
    1.27
    rients
    1.27
    Act Density 0.268%

    No Known Activations