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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Ban" followed by a number (sometimes combined with other words)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Ban."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTAL
    -0.70
    æ©Ł
    -0.69
    ORY
    -0.68
    FORMATION
    -0.67
     gritty
    -0.67
    çīĪ
    -0.66
    paio
    -0.65
    ROR
    -0.64
     Generations
    -0.64
     rendition
    -0.63
    POSITIVE LOGITS
    quet
    1.13
    anas
    1.10
    aji
    0.98
    undo
    0.95
    hammer
    0.95
     Ban
    0.93
    nered
    0.92
    arest
    0.92
    ner
    0.91
    anan
    0.91
    Act Density 0.009%

    No Known Activations