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

    Neuronpedia

    INDEX
    Explanations

    expressions of irrelevance and incongruity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.26
    3:0.08
    4:0.17
    5:0.05
    6:0.02
    7:0.02
    8:0.08
    9:0.09
    10:0.05
    11:0.02
    Negative Logits
    ulhu
    -1.41
    wat
    -1.22
     brightest
    -1.15
     unchecked
    -1.11
    pell
    -1.09
     acad
    -1.08
    urion
    -1.07
    nai
    -1.06
    perm
    -1.06
    estones
    -1.04
    POSITIVE LOGITS
    iment
    1.45
    ption
    1.44
    ception
    1.42
    ilty
    1.35
    ainment
    1.31
    enment
    1.30
    ministic
    1.30
    iments
    1.28
    ishable
    1.27
    itely
    1.26
    Act Density 0.003%

    No Known Activations