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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences with specific characters or symbols like 'Ŀ'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific formatting or structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incorpor
    -0.80
     ende
    -0.76
     controvers
    -0.67
     rundown
    -0.67
     notor
    -0.67
     obser
    -0.66
     mathemat
    -0.66
     range
    -0.64
     inactive
    -0.63
     secretaries
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.18
    ÃĽ
    0.91
    ¯
    0.87
    ï¸
    0.86
    âĢł
    0.83
    °
    0.82
    âĻ
    0.81
    cause
    0.81
    âľ
    0.80
    #$
    0.80
    Act Density 0.153%

    No Known Activations