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

    Neuronpedia

    INDEX
    Explanations

    verbs related to action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.06
    3:0.08
    4:0.09
    5:0.08
    6:0.09
    7:0.08
    8:0.09
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     Franchise
    -2.26
     lawsuit
    -2.11
     Boris
    -1.94
     Kardash
    -1.90
     Ivanka
    -1.78
     sue
    -1.78
     alias
    -1.76
     apology
    -1.75
    dylib
    -1.75
     flats
    -1.73
    POSITIVE LOGITS
    =~=~
    2.79
    UCT
    2.16
    ctory
    2.06
    METHOD
    2.02
    iculty
    1.97
    PDATE
    1.96
     exting
    1.93
    ▬
    1.93
    Experience
    1.89
    �
    1.88
    Act Density 0.000%

    No Known Activations