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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     мәкал
    -0.91
    +#+#
    -0.87
     henvisninger
    -0.84
    EndGlobalSection
    -0.83
    Хьажоргаш
    -0.83
    ⓧ
    -0.82
     linkovi
    -0.82
    ftagPool
    -0.81
     nakalista
    -0.79
    tvguidetime
    -0.75
    POSITIVE LOGITS
     KENT
    0.42
     fact
    0.39
    kaar
    0.38
     ro
    0.38
    NOWLEDG
    0.36
     selera
    0.36
     win
    0.36
    🏻‍♀️
    0.36
     podio
    0.35
     zä
    0.35
    Act Density 1.261%

    No Known Activations