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

    Neuronpedia

    INDEX
    Explanations

    special characters 'âĢ'

    oai_token-act-pair · gpt-3.5-turbo

    the word "can" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shack
    -0.68
     Golem
    -0.65
     blitz
    -0.64
     assemb
    -0.64
     Shib
    -0.63
     guiActiveUnfocused
    -0.63
     spiral
    -0.62
     cyan
    -0.62
     colonial
    -0.62
     dividing
    -0.61
    POSITIVE LOGITS
    Ĵ
    1.02
    £
    0.99
    ı
    0.97
    Ķ
    0.92
    ķ
    0.85
    uve
    0.82
    lege
    0.82
    İ
    0.81
    been
    0.80
    º
    0.80
    Act Density 0.046%

    No Known Activations