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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the central theme or essence of a situation or concept

    oai_token-act-pair · gpt-3.5-turbo

    references to the overarching themes or subjects of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.89
    alian
    -0.85
    prus
    -0.81
    İĭ
    -0.77
    Scroll
    -0.75
    aro
    -0.74
    SON
    -0.74
    é¾
    -0.73
    scl
    -0.72
    DragonMagazine
    -0.72
    POSITIVE LOGITS
     preserving
    1.14
     protecting
    1.13
     educating
    1.05
     overcoming
    1.04
     maximizing
    1.04
     saving
    0.99
     adapting
    0.98
     restoring
    0.98
     finding
    0.97
     ensuring
    0.97
    Act Density 0.071%

    No Known Activations