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

    Neuronpedia

    INDEX
    Explanations

    words related to medical procedures and practices, particularly those involving the handling of remains

    oai_token-act-pair · gpt-3.5-turbo

    words related to animation and humanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ange
    -0.69
     FW
    -0.67
    caps
    -0.67
     Blanc
    -0.66
    holder
    -0.65
    inia
    -0.64
     Mage
    -0.63
     Chap
    -0.61
     Morrow
    -0.60
     Alic
    -0.59
    POSITIVE LOGITS
    endment
    0.84
    DragonMagazine
    0.80
    eral
    0.78
    uli
    0.78
    intage
    0.78
    arily
    0.78
    tsy
    0.76
    ears
    0.76
    quished
    0.76
    ember
    0.76
    Act Density 0.024%

    No Known Activations