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

    Neuronpedia

    INDEX
    Explanations

    references to events and their attributes in a data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peria
    -0.18
    erville
    -0.16
    /lists
    -0.15
    áty
    -0.14
    mono
    -0.14
    apiro
    -0.14
    bÃŃ
    -0.13
    ìĩ
    -0.13
    atatype
    -0.13
    Äħż
    -0.13
    POSITIVE LOGITS
    tle
    0.16
     Bench
    0.15
     defaults
    0.15
     harmon
    0.15
    403
    0.14
    ain
    0.14
    ajan
    0.14
    alle
    0.14
    :
    0.13
     records
    0.13
    Act Density 0.030%

    No Known Activations