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

    Neuronpedia

    INDEX
    Explanations

    elements related to customer reviews and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.00
     Efq
    -0.95
     Monfieur
    -0.88
     Majefty
    -0.85
     Jefus
    -0.84
     ་་
    -0.83
     snippetHide
    -0.83
     CreateTagHelper
    -0.82
    ſelf
    -0.82
     auffi
    -0.80
    POSITIVE LOGITS
    <eos>
    0.62
     )
    0.62
     I
    0.58
     staff
    0.56
     NO
    0.52
     A
    0.51
     
    0.50
     delar
    0.49
     ]
    0.47
    NO
    0.47
    Act Density 0.087%

    No Known Activations