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

    Neuronpedia

    INDEX
    Explanations

    mentions of helpfulness or supportive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iro
    -0.20
    ixer
    -0.16
    éĴ®
    -0.16
    egade
    -0.16
    lor
    -0.14
    adero
    -0.14
    abez
    -0.14
    .tele
    -0.14
    chet
    -0.14
    baru
    -0.14
    POSITIVE LOGITS
    apan
    0.18
    upy
    0.16
    soever
    0.16
    ening
    0.15
    оÑİ
    0.14
    ened
    0.14
     Dude
    0.14
    simulate
    0.14
    éĺª
    0.14
    ness
    0.14
    Act Density 0.005%

    No Known Activations