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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "tone" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yor
    -0.16
    yen
    -0.15
    urch
    -0.15
    a
    -0.14
    e
    -0.14
    ampus
    -0.14
    eck
    -0.14
    cono
    -0.14
    es
    -0.14
    oute
    -0.14
    POSITIVE LOGITS
    nage
    0.27
    ights
    0.19
    neau
    0.19
     Ton
    0.19
     ton
    0.18
    Ton
    0.18
    ality
    0.18
    -ton
    0.18
    IGHT
    0.17
    bsp
    0.17
    Act Density 0.011%

    No Known Activations