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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix "un."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dı
    -0.17
    aft
    -0.15
    crast
    -0.15
    camp
    -0.15
    inner
    -0.15
    оне
    -0.14
    d
    -0.14
    gang
    -0.14
    dress
    -0.14
    cord
    -0.14
    POSITIVE LOGITS
    iversal
    0.23
    tdown
    0.22
    iversit
    0.22
    iverse
    0.21
    iversity
    0.21
    ächst
    0.21
    ecessarily
    0.20
    erals
    0.20
    y
    0.20
    IVERS
    0.19
    Act Density 0.070%

    No Known Activations