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

    Neuronpedia

    INDEX
    Explanations

    words related to creativity and activism

    oai_token-act-pair · gpt-3.5-turbo

    references to creativity and creative expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.71
    HEAD
    -0.67
     Leone
    -0.65
    motion
    -0.65
     Akin
    -0.63
     aside
    -0.62
     regist
    -0.61
     tip
    -0.60
     guidance
    -0.59
    PRESS
    -0.58
    POSITIVE LOGITS
    ured
    1.47
    ures
    1.30
    urer
    1.25
    ions
    1.23
    orship
    1.18
    ivity
    1.18
    urers
    1.18
    ure
    1.18
    orious
    1.17
    urous
    1.13
    Act Density 0.090%

    No Known Activations