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

    Neuronpedia

    INDEX
    Explanations

    the presence of references to leadership roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.09
    2:0.15
    3:0.10
    4:0.04
    5:0.04
    6:0.07
    7:0.06
    8:0.12
    9:0.15
    10:0.06
    11:0.04
    Negative Logits
    nings
    -1.34
    krit
    -1.33
    vertisement
    -1.31
    mys
    -1.30
    eeper
    -1.24
    former
    -1.21
    fixes
    -1.21
     ignition
    -1.16
    inition
    -1.15
    regular
    -1.14
    POSITIVE LOGITS
    nih
    1.33
     istg
    1.28
     Vet
    1.19
     Agg
    1.18
     ENT
    1.17
    ️
    1.14
     Unch
    1.14
     (%)
    1.12
     -----
    1.06
     Nan
    1.06
    Act Density 0.075%

    No Known Activations