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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate difficulty or complexity in tasks and comparisons to trivial matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #+#
    -0.69
    Παραπομπές
    -0.68
     surla
    -0.65
     ffilmiau
    -0.60
     psycopg
    -0.60
    BufferException
    -0.59
     بيها
    -0.59
     "..\..\..\
    -0.58
    DispatchToProps
    -0.58
    NUMX
    -0.58
    POSITIVE LOGITS
     nor
    0.59
    nor
    0.55
    وف
    0.48
    $',
    0.48
     indeed
    0.47
    WICH
    0.46
    :]:
    0.46
    ()]);
    0.46
    BoxShadow
    0.46
     hề
    0.45
    Act Density 0.170%

    No Known Activations