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

    Neuronpedia

    INDEX
    Explanations

    specific keywords and phrases associated with instructions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FSIZE
    -0.17
    edis
    -0.16
    ABA
    -0.15
    証
    -0.15
    Ħĸ
    -0.15
     ÐĿаÑģ
    -0.14
    .scalablytyped
    -0.14
    _fk
    -0.14
     sizes
    -0.14
     поÑģÑĤав
    -0.14
    POSITIVE LOGITS
    quist
    0.18
    zia
    0.18
    ìĤ°
    0.16
     Ub
    0.15
    kes
    0.15
    uation
    0.15
    udo
    0.15
    cstdint
    0.15
    ka
    0.14
     Sparks
    0.14
    Act Density 0.009%

    No Known Activations