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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong positive or negative emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzi
    -0.16
    ogui
    -0.15
    ield
    -0.15
    tember
    -0.14
    Permanent
    -0.14
    enso
    -0.14
    ekk
    -0.14
    ODE
    -0.14
    vla
    -0.14
    ekl
    -0.14
    POSITIVE LOGITS
    itta
    0.15
    entions
    0.15
    jang
    0.15
    .patch
    0.14
    illa
    0.14
    .Prot
    0.14
    rice
    0.14
    ahir
    0.14
    ILLA
    0.14
    çī
    0.13
    Act Density 0.514%

    No Known Activations