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

    Neuronpedia

    INDEX
    Explanations

    references to machines and technology, particularly in contexts involving hacking or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ric
    -0.15
    ạn
    -0.15
    ÅĽmy
    -0.15
    ceptive
    -0.15
    á»ĩ
    -0.14
    usz
    -0.14
    oger
    -0.14
    طة
    -0.14
     crack
    -0.14
    eyim
    -0.14
    POSITIVE LOGITS
    anical
    0.22
    Ñĥв
    0.16
    /bus
    0.16
    -readable
    0.16
    oord
    0.15
     Gilles
    0.15
    Łèĥ½
    0.15
    planation
    0.14
    bach
    0.14
    irut
    0.14
    Act Density 0.074%

    No Known Activations