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

    Neuronpedia

    INDEX
    Explanations

    terms related to non-profit organizations and non-discriminatory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.75
     vettor
    -0.71
     proprement
    -0.69
     rumahnya
    -0.68
     supérieures
    -0.66
     respectivement
    -0.66
     scuro
    -0.65
    DockStyle
    -0.64
     particulières
    -0.62
     doulou
    -0.62
    POSITIVE LOGITS
     non
    3.65
    Non
    3.44
     Non
    3.41
    non
    3.31
     NON
    3.15
    NON
    2.90
    非
    2.58
     非
    2.13
     nons
    2.02
     Nons
    1.96
    Act Density 0.078%

    No Known Activations