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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "witch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edic
    -0.18
    ØŃØ«
    -0.17
    éļĬ
    -0.16
    antom
    -0.16
    ades
    -0.16
    egg
    -0.15
     Rubin
    -0.15
    443
    -0.15
    weight
    -0.14
    heim
    -0.14
    POSITIVE LOGITS
    ertime
    0.20
    SOR
    0.17
    craft
    0.17
    statt
    0.17
    endi
    0.17
    igo
    0.15
    ileaks
    0.15
    ãģĹãģ®
    0.15
    iful
    0.15
    itten
    0.14
    Act Density 0.023%

    No Known Activations