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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.96
     Majefty
    -0.96
    })*/
    -0.89
    ſelves
    -0.89
     itſelf
    -0.89
    ⓧ
    -0.85
     myſelf
    -0.84
    ſelf
    -0.84
    AddTagHelper
    -0.82
     Forumite
    -0.81
    POSITIVE LOGITS
    agine
    0.52
     except
    0.43
    numerusform
    0.42
    に戻る
    0.42
    ană
    0.41
    key
    0.41
    data
    0.41
    Tri
    0.40
    vari
    0.39
    ggen
    0.39
    Act Density 0.047%

    No Known Activations