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

    Neuronpedia

    INDEX
    Explanations

    metadata tags and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.06
    2:0.28
    3:0.05
    4:0.03
    5:0.03
    6:0.07
    7:0.08
    8:0.05
    9:0.06
    10:0.14
    11:0.05
    Negative Logits
    senal
    -2.66
    Vers
    -2.52
    cham
    -2.34
    sea
    -2.18
     Boat
    -2.17
     Prosper
    -2.15
     Gra
    -2.15
    verting
    -2.13
    Gra
    -2.12
     Vers
    -2.11
    POSITIVE LOGITS
     ID
    4.03
     IDs
    3.99
     id
    3.84
    Id
    3.75
    id
    3.72
    ID
    3.39
    IDs
    3.37
     Id
    3.30
     NCT
    2.79
     Nid
    2.69
    Act Density 0.000%

    No Known Activations