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

    Neuronpedia

    INDEX
    Explanations

    references to sketches or drawings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to artistic creation or types of media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urst
    -0.65
     Butterfly
    -0.65
     nig
    -0.64
    stood
    -0.63
     Dee
    -0.63
     Greene
    -0.62
     neglig
    -0.62
     Bild
    -0.62
    alach
    -0.62
    osate
    -0.60
    POSITIVE LOGITS
    earchers
    0.75
    acters
    0.75
    isable
    0.72
    idth
    0.71
    ific
    0.70
    %%%%
    0.70
    inary
    0.69
    izable
    0.69
    myra
    0.68
    hran
    0.66
    Act Density 0.009%

    No Known Activations