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

    Neuronpedia

    INDEX
    Explanations

    titles of research articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utch
    -0.15
    ÎijÎĻ
    -0.15
    allis
    -0.14
    chai
    -0.14
    æ¯ķ
    -0.14
    odes
    -0.13
     Lust
    -0.13
    VML
    -0.13
     gly
    -0.13
    inders
    -0.13
    POSITIVE LOGITS
    ORITY
    0.17
    tit
    0.17
    /title
    0.15
    oldem
    0.15
     title
    0.15
    issy
    0.15
     Tit
    0.14
     Polo
    0.14
     tit
    0.14
     quar
    0.14
    Act Density 0.009%

    No Known Activations