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

    Neuronpedia

    INDEX
    Explanations

    gerunds and present participles of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.05
    3:0.06
    4:0.06
    5:0.28
    6:0.03
    7:0.02
    8:0.05
    9:0.05
    10:0.08
    11:0.09
    Negative Logits
    vertis
    -1.64
    ��
    -1.59
    merce
    -1.58
    conom
    -1.57
     Sno
    -1.57
    achus
    -1.56
     summ
    -1.53
    ngth
    -1.50
    iversary
    -1.47
     Holiday
    -1.46
    POSITIVE LOGITS
    treated
    1.59
    llah
    1.58
    icken
    1.55
    inct
    1.55
    alter
    1.52
     feat
    1.51
    wart
    1.49
    inker
    1.48
     Rodriguez
    1.47
    inka
    1.46
    Act Density 0.000%

    No Known Activations