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

    Neuronpedia

    INDEX
    Explanations

    the verb "go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.06
    3:0.09
    4:0.09
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
     cracking
    -2.29
     freezing
    -2.28
     sizing
    -2.15
     contraction
    -2.08
     whine
    -2.07
     terminating
    -2.06
     laughing
    -2.06
     shutting
    -2.05
     twisting
    -2.04
     shaving
    -2.03
    POSITIVE LOGITS
    quished
    2.33
    occup
    2.29
    Prev
    2.28
    pei
    2.23
    rahim
    2.20
    vre
    2.20
     GOODMAN
    2.19
    enta
    2.16
    arez
    2.15
    redo
    2.14
    Act Density 0.000%

    No Known Activations