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

    Neuronpedia

    INDEX
    Explanations

    specific terms and references related to power dynamics and control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ringe
    -0.17
    iazza
    -0.15
    phants
    -0.15
    ле
    -0.15
    agna
    -0.15
    raud
    -0.15
    ungi
    -0.14
    uchos
    -0.14
    uka
    -0.14
    hots
    -0.14
    POSITIVE LOGITS
     Hanging
    0.14
     exceptions
    0.14
     Maced
    0.14
    umen
    0.13
     Exceptions
    0.13
    ãĢĤ↵↵↵↵↵↵
    0.13
    ÃŃk
    0.13
    ìŀĶ
    0.13
     Griffith
    0.13
    LY
    0.13
    Act Density 0.024%

    No Known Activations