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

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and prepositions used to construct complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.38
    2:0.03
    3:0.04
    4:0.03
    5:0.12
    6:0.02
    7:0.03
    8:0.05
    9:0.06
    10:0.05
    11:0.04
    Negative Logits
    ニ
    -1.90
    taboola
    -1.89
    ジ
    -1.88
    �
    -1.87
    ural
    -1.73
    Recipe
    -1.72
    Tweet
    -1.72
    Sym
    -1.66
    Cor
    -1.62
    Document
    -1.59
    POSITIVE LOGITS
     endif
    1.82
     undecided
    1.81
    haps
    1.76
     insignificant
    1.75
     constitu
    1.73
    theless
    1.71
     subdiv
    1.68
     indifferent
    1.65
     infinitely
    1.64
     econom
    1.63
    Act Density 0.003%

    No Known Activations