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

    Neuronpedia

    INDEX
    Explanations

    symbols and notation related to mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     }_{
    -0.61
    )_{
    -0.53
    <sub>
    -0.51
    othe
    -0.51
    section
    -0.51
    addComponent
    -0.51
     Nis
    -0.49
    ethe
    -0.49
     Unsc
    -0.48
     and
    -0.48
    POSITIVE LOGITS
    [\
    1.66
     $[\
    1.32
     [\
    1.32
    $[\
    1.18
    }[\
    1.16
     [{\
    1.06
     [#
    0.97
    ">[
    0.94
    [:]
    0.88
    [
    0.88
    Act Density 0.495%

    No Known Activations