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

    Neuronpedia

    INDEX
    Explanations

    dialogue and quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icontrol
    -0.16
    rellas
    -0.15
    enders
    -0.15
    Äįku
    -0.14
    ï¸
    -0.14
    ãĤıãģļ
    -0.14
    iao
    -0.14
    oto
    -0.14
    545
    -0.14
    amik
    -0.14
    POSITIVE LOGITS
    alim
    0.16
    å¾Ħ
    0.15
    amus
    0.14
    eden
    0.14
    reuse
    0.13
    ç©į
    0.13
    linger
    0.13
    atak
    0.13
    è¦ļ
    0.13
     dedim
    0.13
    Act Density 0.234%

    No Known Activations