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

    Neuronpedia

    INDEX
    Explanations

    names with specific special characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or placeholder in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.94
    lda
    -0.71
    itably
    -0.70
    ctors
    -0.70
    etheless
    -0.68
    ioned
    -0.68
     censor
    -0.67
     Nam
    -0.67
     Bermuda
    -0.64
     Libyan
    -0.63
    POSITIVE LOGITS
    ¹
    1.22
    º
    1.13
    į
    1.13
    £
    1.13
    ı
    1.11
    ¬
    1.11
    ¡
    1.08
    Ĭ
    1.06
    Ĵ
    1.04
    ħ
    1.04
    Act Density 0.208%

    No Known Activations