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

    Neuronpedia

    INDEX
    Explanations

    expressions of shock and surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actively
    -0.15
    paged
    -0.15
    lisi
    -0.15
    centage
    -0.14
    expert
    -0.14
    ally
    -0.14
    past
    -0.13
    _dual
    -0.13
     Picker
    -0.13
    REM
    -0.13
    POSITIVE LOGITS
    rias
    0.16
     freezes
    0.16
     reaction
    0.15
     surprise
    0.15
    ington
    0.15
    agher
    0.14
     freezing
    0.14
    stag
    0.14
     Spread
    0.14
    à¥įरथ
    0.14
    Act Density 0.282%

    No Known Activations