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

    Neuronpedia

    INDEX
    Explanations

    repeated patterns or sequences in structured data or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     //
    -0.60
     vPvB
    -0.58
    =:
    -0.58
     صوتيه
    -0.57
    .}\
    -0.57
    StructEnd
    -0.55
    '},
    -0.55
     //
    -0.55
     }{\
    -0.55
     \%
    -0.54
    POSITIVE LOGITS
    #
    1.59
    if
    1.27
    try
    1.01
    print
    0.97
    ##
    0.95
    ###
    0.86
    """
    0.86
    '''
    0.85
    ↵
    0.83
    for
    0.82
    Act Density 0.067%

    No Known Activations