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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and questions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oref
    -0.16
    onymous
    -0.16
    agem
    -0.15
    Ĥæķ°
    -0.15
    -cols
    -0.15
    ãĥ¼ãĥł
    -0.15
    ç³
    -0.14
    enco
    -0.14
    ersh
    -0.14
    fram
    -0.14
    POSITIVE LOGITS
    átka
    0.15
    um
    0.14
    ÑĥлÑĮ
    0.14
     Grat
    0.14
    ipay
    0.14
    ronic
    0.14
    igated
    0.14
    \b
    0.13
     therap
    0.13
    anger
    0.13
    Act Density 0.064%

    No Known Activations