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

    Neuronpedia

    INDEX
    Explanations

    specific references related to sports events or news

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to episodes or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }.
    -0.76
    ?).
    -0.74
    )?
    -0.66
     alike
    -0.63
    .).
    -0.61
    !).
    -0.60
    ?".
    -0.58
    ]).
    -0.56
     subconscious
    -0.56
    ).
    -0.55
    POSITIVE LOGITS
    netflix
    0.54
    izont
    0.54
    package
    0.53
    HP
    0.52
    SpaceEngineers
    0.51
    obook
    0.51
    activation
    0.51
    escription
    0.51
    automatic
    0.50
    prints
    0.49
    Act Density 1.105%

    No Known Activations