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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.09
    4:0.08
    5:0.07
    6:0.07
    7:0.09
    8:0.07
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     replay
    -2.13
    uilt
    -1.99
    undy
    -1.93
    ride
    -1.90
    ilts
    -1.89
    bage
    -1.89
     chew
    -1.87
    Contents
    -1.81
    iership
    -1.81
     spo
    -1.78
    POSITIVE LOGITS
     Hai
    2.10
    ios
    1.92
     Majesty
    1.89
    バ
    1.86
     Tomorrow
    1.84
    Angel
    1.84
     Nightmares
    1.80
    ATA
    1.79
    Cra
    1.78
     Cells
    1.75
    Act Density 0.000%

    No Known Activations