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

    Neuronpedia

    INDEX
    Explanations

    sentences where the word "âĢ" is followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    multiple references to a particular individual's influence or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     minim
    -0.78
     cyan
    -0.70
     scatter
    -0.70
     precaution
    -0.67
     maximum
    -0.66
     guiActiveUnfocused
    -0.66
     maxim
    -0.65
     shack
    -0.64
     decomp
    -0.64
    ussian
    -0.63
    POSITIVE LOGITS
    £
    0.96
    perhaps
    0.92
    ı
    0.90
    âĸº
    0.89
    ¢
    0.87
    âĢķ
    0.85
    say
    0.85
    Ĭ
    0.85
    ¡
    0.84
    especially
    0.84
    Act Density 0.607%

    No Known Activations