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

    Neuronpedia

    INDEX
    Explanations

    words related to size or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent individuals or entities associated with power or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TPPStreamerBot
    -0.94
    theless
    -0.92
    stellar
    -0.91
    thia
    -0.90
    cedes
    -0.82
    rss
    -0.80
    amera
    -0.78
    schild
    -0.78
    hemy
    -0.76
    efully
    -0.75
    POSITIVE LOGITS
     arena
    0.92
     boys
    0.89
     guys
    0.87
     brass
    0.83
     thing
    0.82
     ol
    0.81
    gest
    0.79
     guy
    0.79
     leagues
    0.77
     difference
    0.76
    Act Density 0.061%

    No Known Activations