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

    Neuronpedia

    INDEX
    Explanations

    references to specific countries or discussions of national contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĥ½
    -2.71
     ↵
    -2.52
    ↵
    -2.52
    ↵
    -2.52
    -2.52
    -2.52
    ↵↵
    -2.52
    ↵
    -2.52
     ↵
    -2.52
    -2.52
    POSITIVE LOGITS
    wide
    2.43
    men
    2.19
    yard
    1.93
    boat
    1.67
    amer
    1.65
     passer
    1.64
    mega
    1.63
    's
    1.63
    arro
    1.61
    man
    1.61
    Act Density 0.129%

    No Known Activations