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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ban" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SERVICE
    -0.76
    ctl
    -0.74
    æ©Ł
    -0.66
     Generations
    -0.65
     Democr
    -0.65
     PROG
    -0.64
     IMAGES
    -0.63
    OTAL
    -0.63
    paio
    -0.61
    IRE
    -0.61
    POSITIVE LOGITS
    anas
    1.28
    quet
    1.15
    anan
    1.06
    ished
    0.99
    ner
    0.98
    nered
    0.97
    jo
    0.95
    ning
    0.93
    nery
    0.93
    aji
    0.92
    Act Density 0.015%

    No Known Activations