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

    Neuronpedia

    INDEX
    Explanations

    questions comparing quantities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.98
    Obrázky
    -0.95
    Tikang
    -0.85
    TagMode
    -0.85
     itſelf
    -0.85
     ſeveral
    -0.84
    tagHelperRunner
    -0.83
    reportWebVitals
    -0.82
     estekak
    -0.81
     myſelf
    -0.79
    POSITIVE LOGITS
     Who
    0.69
     who
    0.61
    Who
    0.58
     кому
    0.53
    who
    0.52
     or
    0.52
     кто
    0.51
    誰
    0.50
    ↵↵
    0.50
     (
    0.49
    Act Density 0.185%

    No Known Activations