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

    Neuronpedia

    INDEX
    Explanations

    names or parts of names with peculiar characters

    oai_token-act-pair · gpt-3.5-turbo

    the end of segments or sections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incorpor
    -0.81
     secretaries
    -0.75
     targeted
    -0.75
     cones
    -0.72
     succession
    -0.71
     range
    -0.70
     mushroom
    -0.70
     warr
    -0.70
     intercept
    -0.69
    isers
    -0.69
    POSITIVE LOGITS
    ï¸ı
    1.50
    âľ
    1.04
    ï¸
    0.98
    âĻ
    0.97
    âĿ
    0.97
    âĹ
    0.95
     âĢº
    0.94
    âĢ
    0.93
    #
    0.93
    ðŁ
    0.92
    Act Density 0.150%

    No Known Activations