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

    Neuronpedia

    INDEX
    Explanations

    symbolic constructs in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    an
    -1.15
    <i>
    -1.11
    <b>
    -1.01
    r
    -0.98
    le
    -0.97
    k
    -0.97
    in
    -0.97
    es
    -0.94
    K
    -0.90
    ne
    -0.90
    POSITIVE LOGITS
    ("{}
    1.35
    ^(@)
    1.32
     myſelf
    1.30
     themſelves
    1.28
     himſelf
    1.27
     purpoſe
    1.21
     itſelf
    1.20
    BibitemShut
    1.20
     $_"
    1.19
    :{}
    1.17
    Act Density 0.425%

    No Known Activations