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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.27
     Monfieur
    -1.20
     Efq
    -1.16
     Anſ
    -1.10
     Majefty
    -1.10
     myſelf
    -1.10
     raiſ
    -1.07
     becauſe
    -1.06
     Houſe
    -1.04
     uſed
    -1.04
    POSITIVE LOGITS
    -
    0.82
     -
    0.72
    <eos>
    0.72
     (
    0.63
     
    0.59
     '
    0.53
     that
    0.53
     d
    0.53
    ↵
    0.53
     for
    0.51
    Act Density 0.725%

    No Known Activations