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

    Neuronpedia

    INDEX
    Explanations

    statements related to critique or evaluation of performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     culturali
    -0.34
    ectoria
    -0.32
    cessed
    -0.32
     féminine
    -0.31
    jillo
    -0.31
     eléctrico
    -0.30
     femeninos
    -0.29
     eléctricas
    -0.29
     eléctricos
    -0.29
    visitor
    -0.28
    POSITIVE LOGITS
     @"/
    0.57
     surla
    0.56
     للاسماء
    0.54
     Stoke
    0.54
    躇
    0.52
     Sunderland
    0.51
    GetAxis
    0.50
    ppig
    0.50
     manager
    0.50
    underland
    0.50
    Act Density 0.187%

    No Known Activations