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

    Neuronpedia

    INDEX
    Explanations

    titles and headings that use special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    titles of books, movies, or songs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapse
    -0.88
     pressures
    -0.80
     stretched
    -0.78
     spir
    -0.77
     mounts
    -0.77
     limb
    -0.75
     dismiss
    -0.73
     tort
    -0.73
     aroused
    -0.72
     conflicted
    -0.72
    POSITIVE LOGITS
    Operation
    1.43
    76561
    1.18
    STAR
    1.18
    ï¸ı
    1.10
    Occup
    1.10
    Stra
    1.10
    20439
    1.09
    Fore
    1.08
    Ô
    1.08
    ãĥ´ãĤ¡
    1.08
    Act Density 0.172%

    No Known Activations