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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to structure, classification, and elements in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.79
    ’
    -0.36
    <eos>
    -0.32
    '
    -0.29
    λοι
    -0.29
    MathML
    -0.28
    ё
    -0.27
    </b>
    -0.27
    нен
    -0.26
    ´
    -0.26
    POSITIVE LOGITS
     Efq
    0.60
     myſelf
    0.59
     Monfieur
    0.55
     Majefty
    0.54
     Theſe
    0.52
     themſelves
    0.52
     purpoſe
    0.52
     itſelf
    0.51
     Jefus
    0.51
     ſeveral
    0.50
    Act Density 53.244%

    No Known Activations