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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to quotes or significant dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.18
    3:0.05
    4:0.09
    5:0.07
    6:0.08
    7:0.12
    8:0.04
    9:0.04
    10:0.14
    11:0.09
    Negative Logits
    weeney
    -1.68
    uliffe
    -1.66
    andre
    -1.63
    igne
    -1.51
    utherland
    -1.49
    emi
    -1.48
    ato
    -1.48
    utenberg
    -1.44
    uncture
    -1.42
     rhet
    -1.41
    POSITIVE LOGITS
    isphere
    1.51
     aka
    1.39
     flyers
    1.34
     Mecca
    1.33
    iphate
    1.32
     spreads
    1.30
     phenomenon
    1.27
     Bermuda
    1.26
     kicks
    1.25
     Disclosure
    1.25
    Act Density 0.075%

    No Known Activations