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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.07
    3:0.09
    4:0.09
    5:0.07
    6:0.09
    7:0.07
    8:0.07
    9:0.10
    10:0.08
    11:0.09
    Negative Logits
     +/-
    -1.89
     slang
    -1.87
     outage
    -1.82
     ration
    -1.80
     Karachi
    -1.79
     Newfoundland
    -1.78
     metre
    -1.77
     minus
    -1.73
     fret
    -1.71
     sled
    -1.71
    POSITIVE LOGITS
    sych
    1.90
    rov
    1.82
    bringing
    1.79
    ilings
    1.76
    gets
    1.73
    HCR
    1.73
    uph
    1.69
    ideon
    1.69
    VIDIA
    1.68
    assad
    1.68
    Act Density 0.000%

    No Known Activations