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

    Neuronpedia

    INDEX
    Explanations

    the characters 'Ļ' or 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    negations or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.78
     successes
    -0.69
     Seym
    -0.64
     Imag
    -0.64
     Skydragon
    -0.64
     Gutenberg
    -0.64
     Nanto
    -0.64
     Lawn
    -0.63
     Scenes
    -0.63
     Companion
    -0.63
    POSITIVE LOGITS
    ï¸ı
    0.95
    ï¸
    0.91
    sure
    0.88
    hip
    0.87
    agree
    0.85
    âĶĢ
    0.83
    yet
    0.82
    ðŁĺ
    0.81
    ski
    0.80
    le
    0.80
    Act Density 0.213%

    No Known Activations