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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contradiction or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.56
    lccn
    -0.54
    bootstrapcdn
    -0.52
    '},
    -0.52
    '],$
    -0.49
    "":
    -0.48
    __":
    -0.48
    prefixer
    -0.47
    postsleuth
    -0.47
    urop
    -0.47
    POSITIVE LOGITS
    .
    0.58
     useStyles
    0.50
    !
    0.49
    MathML
    0.47
    kapnya
    0.47
    ."
    0.47
    InputTagHelper
    0.45
    onResume
    0.45
    PerPage
    0.45
     Regelung
    0.45
    Act Density 0.817%

    No Known Activations