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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preferences or choices

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    EndContext
    -0.44
     gew
    -0.44
    AddTagHelper
    -0.43
     deta
    -0.43
    Kle
    -0.43
    A
    -0.42
    ffffffff
    -0.40
     Kard
    -0.40
    Dichloropropane
    -0.40
    copyWith
    -0.40
    POSITIVE LOGITS
    出版年
    0.71
    ostante
    0.65
    NOPQRST
    0.65
     espont
    0.62
    gelopen
    0.61
    Parcelize
    0.60
    wikidata
    0.60
    oused
    0.59
    ioutil
    0.58
    bbene
    0.57
    Act Density 0.299%

    No Known Activations