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

    Neuronpedia

    INDEX
    Explanations

    terms related to arrows and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rics
    -0.18
    zik
    -0.17
    stro
    -0.17
    ãĥ³ãĥĦ
    -0.16
    quia
    -0.15
    ìĻ¸
    -0.15
    moid
    -0.15
    isel
    -0.15
    ANTE
    -0.15
    icol
    -0.14
    POSITIVE LOGITS
    ANA
    0.16
     Wings
    0.14
    utra
    0.14
     Pru
    0.14
    asje
    0.14
    éļ
    0.14
    utr
    0.14
    زاÙĨ
    0.14
    leigh
    0.14
     Buen
    0.13
    Act Density 0.026%

    No Known Activations