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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases related to formal agreements or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.06
    4:0.11
    5:0.03
    6:0.06
    7:0.39
    8:0.03
    9:0.03
    10:0.08
    11:0.05
    Negative Logits
    owan
    -1.59
     fame
    -1.53
    xs
    -1.46
    imeo
    -1.43
    avery
    -1.39
    enza
    -1.37
     ·
    -1.34
    bows
    -1.32
     luck
    -1.31
    elight
    -1.31
    POSITIVE LOGITS
    soDeliveryDate
    1.90
     specifications
    1.72
     contingency
    1.71
     elaborate
    1.66
    uggest
    1.64
     strateg
    1.56
     Interpret
    1.53
     timet
    1.53
     prospective
    1.52
     customized
    1.52
    Act Density 0.002%

    No Known Activations