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

    Neuronpedia

    INDEX
    Explanations

    phrases signaling the beginning of a new paragraph or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $.
    -1.12
     doubtnut
    -1.04
     MainAxisSize
    -1.04
    BibitemShut
    -1.03
     lenker
    -1.00
     ་་
    -1.00
     Roskov
    -0.98
     виправивши
    -0.98
    AnimationsModule
    -0.96
    IndentedString
    -0.94
    POSITIVE LOGITS
    For
    1.87
     For
    1.83
    FOR
    1.39
     FOR
    1.30
    for
    1.30
    To
    0.92
     for
    0.92
     Für
    0.87
     Для
    0.87
    ForAll
    0.84
    Act Density 0.118%

    No Known Activations