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

    Neuronpedia

    INDEX
    Explanations

    elements related to product features and specifications in advertisements or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -1.09
    }")
    -0.82
    enumi
    -0.77
    _
    -0.77
    $")
    -0.74
     ]
    -0.72
    $.
    -0.72
    %")
    -0.68
     والتي
    -0.68
    themselves
    -0.68
    POSITIVE LOGITS
     includes
    0.74
     =
    0.73
     +
    0.69
     included
    0.68
    あり
    0.65
    ;
    0.59
     available
    0.58
    :
    0.58
     with
    0.58
     requires
    0.56
    Act Density 0.833%

    No Known Activations