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

    Neuronpedia

    INDEX
    Explanations

    negations and words indicating a lack or an absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riba
    -0.17
    uma
    -0.17
    vester
    -0.17
    еÑĢк
    -0.16
    /cpp
    -0.15
    ãĥ«ãĤ¯
    -0.14
    itz
    -0.14
    IS
    -0.14
    ima
    -0.14
    utch
    -0.14
    POSITIVE LOGITS
    iná
    0.16
    aned
    0.16
    eyen
    0.15
    argon
    0.15
    ÅĤy
    0.14
    ANE
    0.14
    _YES
    0.14
    lobe
    0.14
     McKenzie
    0.14
     TMPro
    0.14
    Act Density 0.001%

    No Known Activations