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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Климат
    -0.60
    Dichloroethane
    -0.53
     Rumuni
    -0.52
    críbete
    -0.52
    ések
    -0.49
     Together
    -0.49
     /\.(
    -0.48
     together
    -0.48
    .
    -0.48
     hemorr
    -0.47
    POSITIVE LOGITS
    ########.
    0.89
    Portail
    0.80
    uxxxx
    0.78
    StructEnd
    0.77
    antaine
    0.76
    */].
    0.76
    LikeLike
    0.74
     المعيارى
    0.72
    GEBURTS
    0.72
     lenker
    0.71
    Act Density 0.443%

    No Known Activations