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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "un" or related prefixes indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cem
    -0.17
    cen
    -0.17
    engin
    -0.15
    entlich
    -0.15
    camp
    -0.14
    okin
    -0.14
    gate
    -0.14
    den
    -0.14
    ucha
    -0.14
    aft
    -0.14
    POSITIVE LOGITS
    erals
    0.23
    iversit
    0.22
    ghi
    0.20
    iverse
    0.20
    iversal
    0.20
    erable
    0.19
    eral
    0.19
    iversity
    0.19
    nel
    0.19
    lap
    0.19
    Act Density 0.082%

    No Known Activations