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

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.78
    ↵↵
    -0.76
     —
    -0.76
     
    -0.75
    er
    -0.75
     (
    -0.72
     "
    -0.72
    _
    -0.72
     -
    -0.71
     “
    -0.70
    POSITIVE LOGITS
     eighteen
    2.70
     nineteen
    2.67
     seventeen
    2.60
     fourteen
    2.60
     sixteen
    2.60
     thirteen
    2.58
     fifteen
    2.52
     twelve
    2.39
     eighty
    2.31
     twenty
    2.31
    Act Density 0.149%

    No Known Activations