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

    Neuronpedia

    INDEX
    Explanations

    phrases related to degrees or levels of intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gram
    -0.18
    igram
    -0.17
    باش
    -0.16
    iton
    -0.15
    borne
    -0.15
    rž
    -0.15
    ascript
    -0.15
    spir
    -0.15
    igrams
    -0.15
    tion
    -0.15
    POSITIVE LOGITS
     Celsius
    0.26
    -degree
    0.20
     Fahrenheit
    0.17
    led
    0.17
    uali
    0.17
    -long
    0.16
    ual
    0.16
    ing
    0.15
    ñana
    0.15
    atsby
    0.15
    Act Density 0.022%

    No Known Activations