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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional responses or expressions of feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.17
    ;base
    -0.14
    ĤŃ
    -0.13
    便
    -0.13
    RIES
    -0.13
    (timeout
    -0.13
    enie
    -0.13
    ÑĨей
    -0.13
    caller
    -0.13
    irlines
    -0.13
    POSITIVE LOGITS
    !,
    0.16
    ?,
    0.16
    chsel
    0.15
    ãĢģãĢģ
    0.15
    lore
    0.13
    ApplicationBuilder
    0.13
     {},
    0.13
     Haz
    0.13
     _,
    0.13
    azi
    0.13
    Act Density 0.260%

    No Known Activations