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

    Neuronpedia

    INDEX
    Explanations

    the character "Ċ" followed by a specific pattern of digits

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.77
    apons
    -0.77
     adolesc
    -0.77
    phia
    -0.75
     Saiyan
    -0.72
    inia
    -0.71
     contempl
    -0.71
     orbiting
    -0.71
    akedown
    -0.69
    zbollah
    -0.68
    POSITIVE LOGITS
    CBC
    1.01
    READ
    0.96
    Owner
    0.91
    Topics
    0.85
    Fans
    0.84
    Ott
    0.83
    Cr
    0.82
     Scotia
    0.82
     Liqu
    0.81
    Hal
    0.81
    Act Density 0.348%

    No Known Activations