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

    Neuronpedia

    INDEX
    Explanations

    assertions or claims that are presented as evident or clear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marsden
    -0.75
    uberge
    -0.67
     automatiquement
    -0.60
     respectivement
    -0.59
    multer
    -0.59
     läng
    -0.58
     automatico
    -0.58
     til
    -0.57
     arrancar
    -0.57
     sóc
    -0.57
    POSITIVE LOGITS
    VIOUS
    1.00
     clearly
    0.91
     Clearly
    0.90
    clearly
    0.90
    Clearly
    0.90
     numberWith
    0.86
    findpost
    0.80
     obviously
    0.80
    obvious
    0.78
     evident
    0.78
    Act Density 0.133%

    No Known Activations