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

    Neuronpedia

    INDEX
    Explanations

    expressions of enjoyment and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynchronously
    -0.20
    lef
    -0.18
    een
    -0.18
    437
    -0.18
    ors
    -0.17
    wards
    -0.16
    lander
    -0.16
    upon
    -0.15
    eters
    -0.15
    -quarters
    -0.15
    POSITIVE LOGITS
    erals
    0.36
    niest
    0.31
    -filled
    0.30
    filled
    0.29
    ghi
    0.28
    nels
    0.28
    icular
    0.28
    -loving
    0.28
    nier
    0.27
    ctors
    0.26
    Act Density 0.028%

    No Known Activations