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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix "un-" indicating negation or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scopic
    -0.16
    electric
    -0.16
    Ñİ
    -0.15
    actively
    -0.15
    æĿ¿
    -0.15
    eus
    -0.14
    opers
    -0.14
    osterone
    -0.14
    .ua
    -0.14
    genus
    -0.14
    POSITIVE LOGITS
    idata
    0.16
    nable
    0.15
    ites
    0.15
    ĸī
    0.15
    ude
    0.15
    ashing
    0.15
    ERTICAL
    0.14
    idos
    0.14
    ities
    0.14
    usal
    0.14
    Act Density 0.039%

    No Known Activations