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

    Neuronpedia

    INDEX
    Explanations

    numerical values and related scientific data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     twenty
    -0.67
     thirteenth
    -0.65
     thirty
    -0.64
     forty
    -0.64
     fifteen
    -0.64
     eighteen
    -0.63
     Thirteenth
    -0.62
     Forty
    -0.61
     milliers
    -0.61
     Thirty
    -0.61
    POSITIVE LOGITS
    TagMode
    0.68
    5
    0.63
    6
    0.63
    4
    0.63
    ]")]
    0.61
    3
    0.61
    7
    0.60
    8
    0.60
    delwed
    0.56
    9
    0.55
    Act Density 0.496%

    No Known Activations