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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and expressions of doubt or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fancy
    -0.17
    inges
    -0.14
     OVERRIDE
    -0.14
    ehler
    -0.14
    .NaN
    -0.14
    kin
    -0.14
    acie
    -0.14
     ún
    -0.14
    æ¬
    -0.13
    ök
    -0.13
    POSITIVE LOGITS
    ạm
    0.18
    phanumeric
    0.16
    apus
    0.16
    uilder
    0.16
    cratch
    0.15
    oxy
    0.15
    izoph
    0.15
    \<^
    0.15
    adele
    0.15
    mention
    0.14
    Act Density 1.197%

    No Known Activations