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

    Neuronpedia

    INDEX
    Explanations

    mentions of development and improvement processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.16
    ivial
    -0.15
    ÑĪин
    -0.14
    errick
    -0.14
    aws
    -0.14
     Äijóng
    -0.13
    meric
    -0.13
    apore
    -0.13
    thouse
    -0.13
    enny
    -0.13
    POSITIVE LOGITS
     further
    0.99
     Further
    0.78
    Further
    0.73
     weiter
    0.62
    è¿Ľä¸ĢæŃ¥
    0.61
     weitere
    0.56
    urther
    0.52
     dále
    0.48
    ãģķãĤīãģ«
    0.47
     farther
    0.47
    Act Density 0.222%

    No Known Activations