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

    Neuronpedia

    INDEX
    Explanations

    letters or character sequences written in Latvian

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, possibly indicating non-standard or non-English text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.79
     compr
    -0.78
    milo
    -0.78
    enegger
    -0.70
     mosqu
    -0.69
     decomp
    -0.68
    ierrez
    -0.68
    usional
    -0.67
    intent
    -0.67
     outcome
    -0.67
    POSITIVE LOGITS
    ħ
    1.24
    ĩ
    1.01
    Į
    0.99
    °
    0.96
    Ĩ
    0.94
    İ
    0.92
    ¨
    0.91
    оÐ
    0.90
    į
    0.89
    ãģĨ
    0.89
    Act Density 0.007%

    No Known Activations