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

    Neuronpedia

    INDEX
    Explanations

    references to constructor calls or initializations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rale
    -0.18
    osi
    -0.18
    izza
    -0.16
    ojis
    -0.16
    ront
    -0.15
    /feed
    -0.14
    zes
    -0.14
    grunt
    -0.14
    ippo
    -0.14
    plorer
    -0.14
    POSITIVE LOGITS
    implify
    0.17
    ucha
    0.16
    ectomy
    0.16
    ecure
    0.15
    ude
    0.15
    alue
    0.14
    hyth
    0.14
     burge
    0.14
    udev
    0.14
     Philosoph
    0.14
    Act Density 0.003%

    No Known Activations