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

    Neuronpedia

    INDEX
    Explanations

    adjectives that convey emotional or qualitative descriptors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ož
    -0.16
    -/
    -0.16
    /post
    -0.15
    каÑģ
    -0.14
    ÙĪرش
    -0.14
    /Area
    -0.14
    DonaldTrump
    -0.14
    immer
    -0.13
    azen
    -0.13
    //{{
    -0.13
    POSITIVE LOGITS
    -looking
    0.35
     yet
    0.32
    ly
    0.30
    ness
    0.29
    lest
    0.27
    yet
    0.25
    NESS
    0.23
     little
    0.23
     enough
    0.22
    looking
    0.21
    Act Density 0.372%

    No Known Activations