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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or requests in a polite manner

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idious
    -0.64
    ccording
    -0.63
    onut
    -0.62
    VERTISEMENT
    -0.62
    ulty
    -0.62
    livious
    -0.60
    rift
    -0.59
    ascus
    -0.59
    abal
    -0.58
    ashtra
    -0.57
    POSITIVE LOGITS
     clarification
    0.86
     to
    0.84
     assurances
    0.79
     thereto
    0.71
     nothing
    0.68
     someone
    0.67
     somebody
    0.66
     something
    0.65
     seeing
    0.61
     luck
    0.60
    Act Density 0.080%

    No Known Activations