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

    Neuronpedia

    INDEX
    Explanations

    references to the word "from" indicating origins or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pcodes
    -0.15
    Ø°Ùĥر
    -0.15
    avel
    -0.15
     Buccane
    -0.14
    inou
    -0.14
    ided
    -0.14
    odos
    -0.14
     Pin
    -0.13
    ilog
    -0.13
    oin
    -0.13
    POSITIVE LOGITS
    hm
    0.15
    affer
    0.15
    äºĭåĭĻ
    0.14
    apsed
    0.14
    vae
    0.14
    roduced
    0.14
    munition
    0.14
    orris
    0.14
    eme
    0.14
    Ń
    0.14
    Act Density 0.071%

    No Known Activations