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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the letter "u" followed by the number 9

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'u'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.80
    =-=-
    -0.79
     Cosponsors
    -0.75
     Attribution
    -0.75
    */(
    -0.74
     initials
    -0.72
     compe
    -0.69
     SERV
    -0.68
     notor
    -0.67
     constants
    -0.67
    POSITIVE LOGITS
    pport
    1.33
    cca
    1.08
    cci
    1.07
    isine
    0.99
    seless
    0.98
    ccess
    0.96
    uru
    0.95
    igi
    0.94
    omo
    0.93
    ji
    0.93
    Act Density 0.026%

    No Known Activations