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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or ownership in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.10
    4:0.11
    5:0.03
    6:0.19
    7:0.16
    8:0.03
    9:0.05
    10:0.10
    11:0.08
    Negative Logits
    adelphia
    -1.35
    soDeliveryDate
    -1.29
    bred
    -1.28
    reditary
    -1.27
    forms
    -1.26
     wreck
    -1.18
    Sync
    -1.16
    wagen
    -1.15
    folk
    -1.15
    Trust
    -1.15
    POSITIVE LOGITS
     ital
    1.73
    phasis
    1.69
     emphasis
    1.58
    arella
    1.53
    imov
    1.51
     understatement
    1.49
    vity
    1.44
     Cohn
    1.44
    .):
    1.43
    ardon
    1.43
    Act Density 0.001%

    No Known Activations