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

    Neuronpedia

    INDEX
    Explanations

    references to specific years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.12
    3:0.09
    4:0.10
    5:0.03
    6:0.10
    7:0.07
    8:0.05
    9:0.05
    10:0.10
    11:0.18
    Negative Logits
    acebook
    -1.45
    iken
    -1.40
     independents
    -1.37
    mercial
    -1.36
    VB
    -1.36
    arsity
    -1.35
    ateurs
    -1.33
     glim
    -1.33
    raph
    -1.32
    antam
    -1.31
    POSITIVE LOGITS
     Kut
    1.54
     Ost
    1.27
     swoop
    1.27
    olkien
    1.26
     Delete
    1.20
     Span
    1.16
     1939
    1.14
     ruth
    1.14
     Dread
    1.13
     conn
    1.12
    Act Density 0.070%

    No Known Activations