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

    Neuronpedia

    INDEX
    Explanations

    instances of text containing specific symbols or characters

    oai_token-act-pair · gpt-3.5-turbo

    repeated special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.76
    hare
    -0.73
    matic
    -0.67
     similarities
    -0.66
     gist
    -0.63
    orial
    -0.63
     primates
    -0.63
    tone
    -0.62
     partnerships
    -0.61
     suit
    -0.60
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.17
    ľ
    1.11
    ĸ
    0.93
    ļ
    0.93
    ª
    0.93
    âĶĢâĶĢâĶĢâĶĢ
    0.92
    Ĺ
    0.90
    ¼
    0.90
    ¸
    0.89
    Ĭ
    0.86
    Act Density 0.256%

    No Known Activations