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

    Neuronpedia

    INDEX
    Explanations

    characters with special symbols and numbers

    oai_token-act-pair · gpt-3.5-turbo

    special characters or extended Unicode characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.84
    aminer
    -0.70
     Carbuncle
    -0.67
    isode
    -0.66
     Nam
    -0.66
     tremend
    -0.65
     scatter
    -0.63
    itably
    -0.62
     venture
    -0.62
     cloaked
    -0.61
    POSITIVE LOGITS
    į
    1.24
    º
    1.24
    ¹
    1.19
    ¡
    1.14
    ı
    1.11
    »
    1.11
    £
    1.10
    ¬
    1.09
    ½
    1.08
    Į
    1.05
    Act Density 0.238%

    No Known Activations