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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.64
     utafitiHapana
    -0.60
     fun
    -0.50
    ⓧ
    -0.50
    Cyfeiriadau
    -0.49
    AnchorTagHelper
    -0.49
     виправивши
    -0.48
     مشين
    -0.47
     nom
    -0.46
     national
    -0.46
    POSITIVE LOGITS
     vectorielles
    0.67
     plufieurs
    0.66
    Története
    0.63
    uksessa
    0.63
     générations
    0.63
     choisis
    0.63
     originais
    0.62
    ConstraintMaker
    0.62
     auroit
    0.61
     vectorielle
    0.61
    Act Density 0.365%

    No Known Activations