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

    Neuronpedia

    INDEX
    Explanations

    words related to poetry and literary works

    oai_token-act-pair · gpt-3.5-turbo

    references to poetry and literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.85
     clamp
    -0.81
    erate
    -0.73
    zinski
    -0.70
     twitch
    -0.69
    ticket
    -0.68
    AX
    -0.68
    adjusted
    -0.66
     Gamble
    -0.66
    AMI
    -0.65
    POSITIVE LOGITS
     poems
    1.45
     laureate
    1.34
     poetry
    1.33
     poem
    1.29
     poets
    1.28
     manuscripts
    1.26
     manuscript
    1.23
     anthology
    1.21
     aloud
    1.18
     poet
    1.14
    Act Density 0.159%

    No Known Activations