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

    Neuronpedia

    INDEX
    Explanations

    punctuation and dialogue markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Germ
    -0.15
     Hum
    -0.14
     Fot
    -0.14
    arta
    -0.13
    irtual
    -0.13
     Mens
    -0.13
    ruh
    -0.13
     Warm
    -0.13
    meni
    -0.13
    vars
    -0.12
    POSITIVE LOGITS
    s
    0.18
    erto
    0.15
    té
    0.15
    rades
    0.15
    å©·
    0.14
    emax
    0.14
    ÏĦον
    0.14
    alling
    0.14
    sink
    0.14
    acon
    0.14
    Act Density 0.045%

    No Known Activations