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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values or indicators of distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tility
    -0.14
    STRUCTOR
    -0.14
    bÃŃr
    -0.14
    JEXEC
    -0.14
    olu
    -0.14
    姫
    -0.14
    undra
    -0.13
     %-
    -0.13
    474
    -0.13
    éĢģæĸĻçĦ¡æĸĻ
    -0.13
    POSITIVE LOGITS
    Callable
    0.17
    ivid
    0.14
    .snapshot
    0.14
    ìĥģ
    0.14
    azzi
    0.13
    7
    0.13
    \Context
    0.13
    ilip
    0.13
    antas
    0.13
    actory
    0.13
    Act Density 0.032%

    No Known Activations