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

    Neuronpedia

    INDEX
    Explanations

    comparative symbols and conditions related to numerical evaluations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    l
    -0.76
    </i>
    -0.73
    quad
    -0.72
    ’
    -0.72
    $
    -0.71
    <eos>
    -0.71
    ,”
    -0.70
    n
    -0.70
     “
    -0.69
    ”
    -0.68
    POSITIVE LOGITS
     myſelf
    1.45
     Efq
    1.38
     Theſe
    1.32
     themſelves
    1.27
    ^(@)
    1.24
     Jefus
    1.18
     himſelf
    1.17
    Lycka
    1.11
    ſelves
    1.09
     purpoſe
    1.09
    Act Density 0.005%

    No Known Activations