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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs expressing inevitability and importance

    oai_token-act-pair · gpt-3.5-turbo

    affirmative statements and descriptors related to events and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viz
    -0.71
    views
    -0.65
    pled
    -0.64
    wrote
    -0.63
     peers
    -0.62
     amounts
    -0.61
    SpaceEngineers
    -0.61
    ancock
    -0.61
    liest
    -0.61
    arlane
    -0.61
    POSITIVE LOGITS
     abound
    0.87
    cussion
    0.74
    senal
    0.73
     indeed
    0.67
    Ĥİ
    0.66
     EXT
    0.65
    Ń·
    0.64
    ©¶æ
    0.64
    oros
    0.64
    ateurs
    0.63
    Act Density 0.727%

    No Known Activations