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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ista
    -0.18
    idth
    -0.17
    лÑİб
    -0.16
    ItemType
    -0.16
    line
    -0.15
    uelles
    -0.15
    ils
    -0.15
    ÑĩаÑģно
    -0.14
     behalf
    -0.14
     sắc
    -0.14
    POSITIVE LOGITS
    /dis
    0.22
    /lo
    0.20
    able
    0.19
    ably
    0.18
    -minded
    0.17
    elihood
    0.17
     latter
    0.16
    WISE
    0.16
    ewise
    0.15
     unto
    0.15
    Act Density 0.050%

    No Known Activations