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

    Neuronpedia

    INDEX
    Explanations

    specific numerical data and measurements related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vill
    -0.17
    lyn
    -0.16
    izza
    -0.15
    izzas
    -0.14
    ernaut
    -0.14
    è¡
    -0.14
     Burst
    -0.14
    ant
    -0.14
    round
    -0.13
    æ®Ĭ
    -0.13
    POSITIVE LOGITS
     otherwise
    0.18
    otherwise
    0.15
    indow
    0.15
    (ib
    0.15
    zhou
    0.15
    jis
    0.14
    zes
    0.14
    .scalablytyped
    0.14
     Otherwise
    0.14
     OTHERWISE
    0.14
    Act Density 0.233%

    No Known Activations