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

    Neuronpedia

    INDEX
    Explanations

    instances of ASCII art

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of a particular character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     writ
    -0.73
     vulner
    -0.72
     limb
    -0.70
     staggered
    -0.65
     ages
    -0.65
     Gardens
    -0.64
     Vog
    -0.64
     division
    -0.64
     strat
    -0.63
     builders
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.29
    Ô
    1.26
    ãĥĥãĥī
    1.13
    ï¸
    1.12
    ËĪ
    1.11
    vernment
    1.09
    lean
    1.09
    âĹ¼
    1.07
    SpaceEngineers
    1.03
    ðĿ
    0.98
    Act Density 0.054%

    No Known Activations