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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causal relationships or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inand
    -0.15
    ogie
    -0.14
    agini
    -0.14
    idar
    -0.13
    lients
    -0.13
    arendra
    -0.13
    oog
    -0.13
    tec
    -0.13
    odos
    -0.13
    ãĥĨãĤ£
    -0.13
    POSITIVE LOGITS
    ulton
    0.16
    abet
    0.15
    eneric
    0.15
    errat
    0.15
    erten
    0.15
    349
    0.15
    зÑĭ
    0.15
    edeki
    0.15
    577
    0.14
    è¡¡
    0.14
    Act Density 0.055%

    No Known Activations