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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or positive sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.18
    elry
    -0.17
    ildo
    -0.17
    .onViewCreated
    -0.16
    -anchor
    -0.15
    egas
    -0.15
    erate
    -0.15
    amage
    -0.15
    elig
    -0.14
    brtc
    -0.14
    POSITIVE LOGITS
    aura
    0.16
    ette
    0.14
     Pole
    0.14
    riel
    0.14
     Heroes
    0.14
    ness
    0.13
     trivia
    0.13
    les
    0.13
     slowing
    0.13
     Experts
    0.13
    Act Density 0.007%

    No Known Activations