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

    Neuronpedia

    INDEX
    Explanations

    references to higher levels of quality or standards in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.04
    4:0.19
    5:0.03
    6:0.20
    7:0.21
    8:0.03
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
    fram
    -1.63
    taboola
    -1.56
    area
    -1.42
    primary
    -1.41
    count
    -1.41
     sshd
    -1.35
    abin
    -1.34
    map
    -1.34
    cyclopedia
    -1.31
    ranking
    -1.29
    POSITIVE LOGITS
     impunity
    1.49
     fame
    1.42
     sentimental
    1.41
     Opinion
    1.34
     metaphysical
    1.33
    IENCE
    1.29
     notions
    1.28
     youthful
    1.28
     infancy
    1.27
    enance
    1.27
    Act Density 0.001%

    No Known Activations