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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and reactions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    365
    -0.15
     clums
    -0.14
    alous
    -0.14
    缼
    -0.14
    SEQU
    -0.14
    unsafe
    -0.13
    .sax
    -0.13
    hey
    -0.13
     меÑĪ
    -0.13
    lediÄŁi
    -0.13
    POSITIVE LOGITS
     sigh
    0.32
     sighed
    0.27
     frustration
    0.27
     gro
    0.23
     frustrations
    0.22
     frustrated
    0.22
     shaking
    0.21
     despair
    0.20
    gro
    0.20
     rolling
    0.20
    Act Density 0.296%

    No Known Activations