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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships to basic arithmetic or mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ––
    -0.88
     NDEBUG
    -0.85
    —
    -0.85
    ​—
    -0.82
     quæ
    -0.81
    ‒
    -0.81
    —”
    -0.80
     ―――――
    -0.80
     yalnızca
    -0.79
     ſhould
    -0.79
    POSITIVE LOGITS
     alot
    1.21
     loosing
    1.20
     todays
    1.06
     didalam
    1.05
     میتوان
    1.02
     coté
    1.01
     thier
    0.99
    慢慢的
    0.95
     diatas
    0.93
     pò
    0.87
    Act Density 1.591%

    No Known Activations