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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming structures and errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.56
    -
    -0.53
    ‘
    -0.49
    '
    -0.48
     ‘
    -0.46
    !
    -0.42
    ”
    -0.42
    </strong>
    -0.42
     [...]
    -0.41
    …
    -0.41
    POSITIVE LOGITS
    InitVars
    0.90
    Personensuche
    0.88
    Personendaten
    0.82
     pinulongan
    0.82
     pleaſure
    0.80
     snippetHide
    0.79
     purpoſe
    0.78
    amaño
    0.78
     للاسماء
    0.78
     AssemblyCulture
    0.78
    Act Density 0.652%

    No Known Activations