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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their experiences or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.14
    3:0.11
    4:0.27
    5:0.04
    6:0.05
    7:0.14
    8:0.03
    9:0.05
    10:0.06
    11:0.04
    Negative Logits
    onomous
    -1.50
     consulted
    -1.37
    undai
    -1.32
    lected
    -1.29
     summoned
    -1.26
     Charg
    -1.25
     outing
    -1.25
    quartered
    -1.24
     sidelined
    -1.23
     dismantled
    -1.22
    POSITIVE LOGITS
    stuff
    1.58
     stuff
    1.41
     crap
    1.41
     anyways
    1.41
     anymore
    1.39
    killers
    1.36
     wrong
    1.36
    selves
    1.35
    farious
    1.34
     rather
    1.32
    Act Density 0.203%

    No Known Activations