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

    Neuronpedia

    INDEX
    Explanations

    words indicating popularity or notoriety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç½²
    -0.19
    eldorf
    -0.17
    æĬŀ
    -0.15
    ocab
    -0.15
    VES
    -0.15
    odega
    -0.14
    atto
    -0.14
    uevo
    -0.14
    adoo
    -0.13
     olsun
    -0.13
    POSITIVE LOGITS
     Rot
    0.16
     rot
    0.15
    round
    0.15
    NAL
    0.15
    /Library
    0.14
    rot
    0.14
     Blanc
    0.14
    imli
    0.14
    ENDER
    0.14
    SY
    0.14
    Act Density 0.011%

    No Known Activations