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

    Neuronpedia

    INDEX
    Explanations

    items characterized by their sweetness or flatness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -1.42
    SBATCH
    -1.22
    MessageTagHelper
    -1.20
     متعلقه
    -1.14
    Дереккөздер
    -1.10
     виправивши
    -1.10
     itſelf
    -1.08
    المراجع
    -1.06
    rungsseite
    -1.06
    Życiorys
    -1.04
    POSITIVE LOGITS
     flat
    0.80
    -
    0.79
    ة
    0.79
     White
    0.76
     Flat
    0.73
    K
    0.72
    ness
    0.70
     thin
    0.69
    P
    0.69
     Bad
    0.67
    Act Density 0.068%

    No Known Activations