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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entirety
    -0.66
     showcased
    -0.65
     incentiv
    -0.63
     showcase
    -0.60
     impactful
    -0.60
     ️
    -0.59
     ―――――
    -0.59
    ️
    -0.58
     showcasing
    -0.58
     microbiome
    -0.57
    POSITIVE LOGITS
     muß
    0.78
     daß
    0.65
     läßt
    0.57
     Miß
    0.57
     müßte
    0.56
    faßt
    0.51
     mußte
    0.49
     Daß
    0.49
     skall
    0.48
     Schluß
    0.47
    Act Density 2.467%

    No Known Activations