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

    Neuronpedia

    INDEX
    Explanations

    the word "whatsoever."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the absence of something or the concept of "nothingness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    po
    -0.78
    por
    -0.70
    eg
    -0.68
    yi
    -0.66
     Ou
    -0.66
    ula
    -0.65
    ett
    -0.65
    ulative
    -0.64
    ku
    -0.64
    pel
    -0.64
    POSITIVE LOGITS
    soever
    1.25
    wcsstore
    1.19
     whatsoever
    1.15
    THING
    0.98
    ĸļ
    0.90
    lihood
    0.82
    £ı
    0.81
     imaginable
    0.81
     else
    0.81
    swer
    0.80
    Act Density 0.004%

    No Known Activations