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

    Neuronpedia

    INDEX
    Explanations

    connections between concepts and the consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymm
    -0.16
    fak
    -0.15
     Ellison
    -0.14
    ool
    -0.14
    ãĥ¯ãĥ¼
    -0.14
    arus
    -0.14
    mür
    -0.13
     Vie
    -0.13
    ia
    -0.13
    itan
    -0.13
    POSITIVE LOGITS
    _due
    0.17
    -www
    0.16
     ÐĿаÑģ
    0.15
    alog
    0.14
    achu
    0.14
    lland
    0.14
    privacy
    0.14
    chy
    0.14
    _pointer
    0.14
    ugo
    0.14
    Act Density 0.005%

    No Known Activations