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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to competition and evaluation results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    нÑĸв
    -0.16
    orra
    -0.14
    ÑĨин
    -0.14
    ORA
    -0.14
    ظÙĬÙģ
    -0.14
    /native
    -0.14
    anden
    -0.14
    rice
    -0.14
    ModelAttribute
    -0.14
    _ALWAYS
    -0.13
    POSITIVE LOGITS
    acho
    0.16
    yard
    0.15
     points
    0.14
     Hass
    0.14
    arts
    0.14
    okit
    0.14
     Encounter
    0.14
    ga
    0.13
    .IC
    0.13
    ð
    0.13
    Act Density 0.100%

    No Known Activations