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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or audience, particularly in a conversational or advising context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.14
    ει
    -0.14
    ussen
    -0.14
    icle
    -0.14
    amp
    -0.14
    foot
    -0.14
    andon
    -0.13
    æ¥Ń
    -0.13
    atti
    -0.13
    line
    -0.13
    POSITIVE LOGITS
    ’re
    0.27
    're
    0.24
    'll
    0.23
    ’ll
    0.23
    -même
    0.22
    've
    0.20
    ’ve
    0.20
    åĢij
    0.20
    /us
    0.20
    nger
    0.20
    Act Density 0.457%

    No Known Activations