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

    Neuronpedia

    INDEX
    Explanations

    words related to colors

    oai_token-act-pair · gpt-3.5-turbo

    references to pale-colored items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ACTIONS
    -0.66
     loudly
    -0.63
    æ©Ł
    -0.62
     loose
    -0.62
     malfunction
    -0.61
    DOM
    -0.60
    ÄŁ
    -0.60
     jammed
    -0.57
    ////
    -0.56
     Sequence
    -0.55
    POSITIVE LOGITS
    olithic
    1.51
    ozo
    1.17
    ohyd
    1.10
    ocl
    1.00
    ogen
    1.00
    ogram
    0.97
    ogene
    0.96
    opath
    0.96
    ont
    0.95
    croft
    0.94
    Act Density 0.034%

    No Known Activations