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

    Neuronpedia

    INDEX
    Explanations

    questions directed at the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.06
    4:0.07
    5:0.03
    6:0.04
    7:0.39
    8:0.04
    9:0.04
    10:0.07
    11:0.11
    Negative Logits
    ante
    -1.71
    encers
    -1.53
    akery
    -1.51
    cases
    -1.49
    bery
    -1.49
    vity
    -1.48
    internet
    -1.46
     pools
    -1.45
    ema
    -1.44
    iversity
    -1.42
    POSITIVE LOGITS
     favorably
    1.79
     outcome
    1.62
     constitu
    1.62
     pros
    1.57
     aloud
    1.56
     sugg
    1.52
     proposition
    1.50
     externalToEVAOnly
    1.43
     Rated
    1.43
     Zup
    1.40
    Act Density 0.005%

    No Known Activations