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

    Neuronpedia

    INDEX
    Explanations

    linguistic markers and structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aye
    -0.17
    aki
    -0.16
    prav
    -0.16
    jerne
    -0.14
    exampleInput
    -0.14
     Class
    -0.13
     anomal
    -0.13
    brid
    -0.13
     gameTime
    -0.13
    orge
    -0.13
    POSITIVE LOGITS
     Bereich
    0.21
     Beitrag
    0.19
     Gang
    0.18
    punkt
    0.17
    ismus
    0.16
    ivism
    0.16
     Blick
    0.16
     Ort
    0.16
     Countdown
    0.15
     Einsatz
    0.15
    Act Density 0.037%

    No Known Activations