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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or smiling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .localized
    -0.15
    лава
    -0.15
    iquid
    -0.15
    aktu
    -0.15
    xon
    -0.14
    stroy
    -0.14
    unas
    -0.14
    jee
    -0.14
    falls
    -0.14
    lod
    -0.13
    POSITIVE LOGITS
     broad
    0.29
     ear
    0.28
     widest
    0.28
     wide
    0.27
    Broad
    0.26
     Broad
    0.26
     beam
    0.25
     broadly
    0.25
    -wide
    0.24
     Wide
    0.24
    Act Density 0.112%

    No Known Activations