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

    Neuronpedia

    INDEX
    Explanations

    words containing the prefix "un-"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the prefix "un-" indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     briefs
    -0.78
    OPLE
    -0.77
    anwhile
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.74
    hetti
    -0.71
     Tut
    -0.70
     Away
    -0.68
     Dynamics
    -0.66
     MX
    -0.66
     Blitz
    -0.65
    POSITIVE LOGITS
    balanced
    1.29
    ruly
    1.23
    assuming
    1.20
    ifying
    1.16
    apolog
    1.14
    availability
    1.14
    organized
    1.13
    cles
    1.12
    classified
    1.10
    earned
    1.09
    Act Density 0.028%

    No Known Activations