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

    Neuronpedia

    INDEX
    Explanations

    mathematical and/or programming text

    oai_token-act-pair · gemini-2.0-flash

    unusual or non-standard words and terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Dickson
    -0.51
    rime
    -0.51
     Glob
    -0.51
     x
    -0.50
    x
    -0.49
     root
    -0.49
    itoneal
    -0.47
     Flanagan
    -0.47
     endogenous
    -0.47
    tuce
    -0.47
    POSITIVE LOGITS
    Хьажоргаш
    0.72
     referrerpolicy
    0.72
    Hozzáférés
    0.70
    OrBuilder
    0.62
    tvguidetime
    0.61
    istoitu
    0.60
    Vidite
    0.59
    didSet
    0.59
    DMETHOD
    0.58
    `,
    0.57
    Act Density 6.142%

    No Known Activations