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

    Neuronpedia

    INDEX
    Explanations

    names with special characters, possibly in the context of addresses or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palestin
    -0.66
     precaution
    -0.62
     reproduction
    -0.62
     maximum
    -0.62
     Malta
    -0.62
     jog
    -0.62
     sacrific
    -0.62
     paperback
    -0.61
     recomb
    -0.61
     vulner
    -0.60
    POSITIVE LOGITS
    ï¸
    0.98
    iversary
    0.93
    ï¸ı
    0.93
    tre
    0.90
    alone
    0.83
    lime
    0.82
    creator
    0.82
    own
    0.81
    worthiness
    0.81
    REDACTED
    0.81
    Act Density 0.295%

    No Known Activations