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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.01
    2:0.07
    3:0.22
    4:0.05
    5:0.02
    6:0.17
    7:0.12
    8:0.04
    9:0.04
    10:0.11
    11:0.06
    Negative Logits
    ></
    -1.58
    eteria
    -1.57
    ['
    -1.51
    encers
    -1.51
     meanwhile
    -1.48
     gangs
    -1.47
     Corinth
    -1.47
     adultery
    -1.44
     rolls
    -1.44
     tow
    -1.41
    POSITIVE LOGITS
    ruby
    1.66
    ordial
    1.65
     Satoshi
    1.53
    oulos
    1.48
    sat
    1.44
     mosqu
    1.43
     IPM
    1.38
     opio
    1.38
     RELE
    1.38
     insightful
    1.36
    Act Density 0.002%

    No Known Activations