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

    Neuronpedia

    INDEX
    Explanations

    passive constructions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.05
    2:0.08
    3:0.09
    4:0.08
    5:0.08
    6:0.08
    7:0.07
    8:0.09
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     manifest
    -1.89
     prevail
    -1.89
     advoc
    -1.83
     affecting
    -1.76
     favor
    -1.75
     impacting
    -1.73
     ration
    -1.73
     conserve
    -1.73
     bold
    -1.71
     favour
    -1.71
    POSITIVE LOGITS
    ioch
    1.86
    76561
    1.86
    XT
    1.84
     Bridgewater
    1.79
    ibrary
    1.79
    ector
    1.77
    HAM
    1.76
    NES
    1.72
    ENE
    1.71
    OX
    1.67
    Act Density 0.000%

    No Known Activations