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

    Neuronpedia

    INDEX
    Explanations

    occurrences of colors and shapes within data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    h
    -0.16
    OND
    -0.14
    o
    -0.14
    iom
    -0.14
    i
    -0.14
    oader
    -0.14
    nets
    -0.14
     tort
    -0.14
    vais
    -0.14
    аÑĩе
    -0.14
    POSITIVE LOGITS
    phies
    0.15
    èĤ²
    0.15
    avad
    0.14
    ngen
    0.14
    astos
    0.14
    -FIRST
    0.14
    /Peak
    0.14
    kaç
    0.14
    ahrain
    0.13
    DCALL
    0.13
    Act Density 0.003%

    No Known Activations