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

    Neuronpedia

    INDEX
    Explanations

    phrases containing specific characters such as brackets or punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    closing brackets or delimiters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.99
    etsy
    -0.77
    ĸļ
    -0.75
    İĭ
    -0.74
    sts
    -0.72
    Ļ½
    -0.72
     manif
    -0.71
     telev
    -0.70
     arte
    -0.68
    iae
    -0.68
    POSITIVE LOGITS
    worthiness
    0.80
    Management
    0.77
    GROUP
    0.73
    ],
    0.73
    TPS
    0.72
     PsyNet
    0.71
    ])
    0.70
    ...]
    0.70
     Uriel
    0.69
    LOG
    0.69
    Act Density 0.054%

    No Known Activations