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

    Neuronpedia

    INDEX
    Explanations

    expressions of ambiguity or vagueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atoi
    -0.17
     Licht
    -0.15
    kus
    -0.15
    erge
    -0.14
    .pm
    -0.14
    inka
    -0.14
    ulus
    -0.14
     Joi
    -0.13
     Enumerable
    -0.13
    ãĥªãĥ³ãĤ¯
    -0.13
    POSITIVE LOGITS
     Ster
    0.17
    oreach
    0.16
    aggio
    0.15
    leting
    0.15
     Marks
    0.14
    æ¸Ī
    0.14
    ÃŃsticas
    0.14
    stery
    0.14
     Millenn
    0.13
    abant
    0.13
    Act Density 0.087%

    No Known Activations