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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "interesting" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    нг
    -0.18
    imas
    -0.15
    elan
    -0.15
    uda
    -0.14
    ldr
    -0.14
    ruba
    -0.14
    renders
    -0.14
    ikers
    -0.13
     Wie
    -0.13
    urent
    -0.13
    POSITIVE LOGITS
    ly
    0.18
    emma
    0.16
    egg
    0.15
    /conf
    0.15
    going
    0.14
    nes
    0.14
    rippling
    0.14
    ioctl
    0.14
    ayi
    0.14
    ácil
    0.14
    Act Density 0.038%

    No Known Activations