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

    Neuronpedia

    INDEX
    Explanations

    phrases related to anatomical structures, specifically wings

    oai_token-act-pair · gpt-3.5-turbo

    references to "wings"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cumber
    -0.85
     Scotia
    -0.77
     Samoa
    -0.69
     Haram
    -0.67
     Tycoon
    -0.65
     Uz
    -0.65
     Kurd
    -0.63
     Garfield
    -0.63
     Lange
    -0.62
     Takeru
    -0.62
    POSITIVE LOGITS
    tip
    1.65
    tips
    1.47
    nuts
    1.40
    nut
    1.36
    pan
    1.23
    edly
    1.04
    bill
    0.99
    pipe
    0.99
    walker
    0.97
    lets
    0.93
    Act Density 0.044%

    No Known Activations