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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating positive evaluations or assessments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    omock
    -0.62
    gonic
    -0.61
    FTFY
    -0.61
    NotSupported
    -0.60
     createSprite
    -0.57
    lemented
    -0.53
    accompag
    -0.53
    FormTagHelper
    -0.50
    contributors
    -0.50
    ANNES
    -0.50
    POSITIVE LOGITS
    Portale
    0.57
    ?」
    0.53
     actionTypes
    0.52
    ?>">
    0.52
    laquo
    0.50
    ؟!
    0.50
    了口气
    0.50
    ✨:
    0.49
    ؟
    0.49
    ToAction
    0.48
    Act Density 0.016%

    No Known Activations