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

    Neuronpedia

    INDEX
    Explanations

    negation phrases, particularly the use of "ain't"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    usage of ain't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (©
    -0.45
    harapkan
    -0.44
     nôtre
    -0.42
     nouvel
    -0.42
     ostavi
    -0.39
    îtra
    -0.37
     idé
    -0.37
    StateToProps
    -0.36
     vêtement
    -0.36
     visão
    -0.35
    POSITIVE LOGITS
     aint
    0.90
    ########.
    0.82
     ain
    0.80
    Ain
    0.75
     Ain
    0.75
    LookAnd
    0.71
     AIN
    0.69
    bootstrapcdn
    0.61
    RefNanny
    0.60
     StringTokenizer
    0.60
    Act Density 0.003%

    No Known Activations