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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific terms, particularly in the context of experimental results or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дописавши
    -0.74
    "")
    -0.69
    "):
    -0.68
    >')
    -0.67
    '')
    -0.66
    %")
    -0.65
    kuuta
    -0.65
    .”)
    -0.64
    /')
    -0.62
    )$_
    -0.61
    POSITIVE LOGITS
    ,
    1.29
    (),
    1.08
    !,
    1.01
    ?,
    1.01
    $,
    0.98
     "",
    0.98
    ',
    0.97
     [],
    0.96
     {},
    0.95
     '',
    0.92
    Act Density 1.309%

    No Known Activations