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

    Neuronpedia

    INDEX
    Explanations

    inquiries about understanding or learning more about a situation or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibbon
    -0.20
    inos
    -0.16
    اÙĤÙĦ
    -0.16
    berger
    -0.15
     FA
    -0.14
    hpp
    -0.14
    chet
    -0.14
    eczy
    -0.14
    _ABI
    -0.14
    erli
    -0.13
    POSITIVE LOGITS
     exactly
    0.32
     Exactly
    0.25
    Exactly
    0.22
     precisely
    0.20
    eca
    0.17
     pÅĻesnÄĽ
    0.17
     genau
    0.17
    actly
    0.17
    TF
    0.17
     exact
    0.16
    Act Density 0.127%

    No Known Activations