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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Umgang
    -0.42
     useStyles
    -0.42
     poj
    -0.40
     terakhir
    -0.39
    ViewBag
    -0.39
     seuls
    -0.38
    ︎
    -0.38
     résine
    -0.38
     teneur
    -0.38
     seules
    -0.38
    POSITIVE LOGITS
     fail
    0.68
     regard
    0.66
     prejudice
    0.65
     hesitation
    0.65
     exception
    0.65
     recourse
    0.60
     interruption
    0.57
     Without
    0.57
    Without
    0.57
    IsContent
    0.56
    Act Density 0.157%

    No Known Activations