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

    Neuronpedia

    INDEX
    Explanations

    connector words and prepositions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.13
    3:0.06
    4:0.08
    5:0.03
    6:0.05
    7:0.32
    8:0.05
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
     batches
    -1.77
    effic
    -1.73
     effic
    -1.70
    RIP
    -1.69
     pharmacies
    -1.60
    encies
    -1.53
    ishable
    -1.49
    DERR
    -1.49
    products
    -1.48
    abolic
    -1.48
    POSITIVE LOGITS
     aisle
    1.95
    sect
    1.71
     fray
    1.71
     passionately
    1.65
     relegation
    1.57
    emate
    1.55
    cair
    1.55
    onds
    1.54
    ulhu
    1.53
    aito
    1.52
    Act Density 0.000%

    No Known Activations