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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical expressions or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.58
    </blockquote>
    -0.53
     comp
    -0.49
    ].
    -0.49
    .*;
    -0.49
    。
    -0.49
    XXXXXXXX
    -0.48
    ).
    -0.46
    sibili
    -0.45
    <eos>
    -0.45
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    1.19
     nahilalakip
    1.03
     itſelf
    0.98
     Majefty
    0.96
     صوتيه
    0.93
    __(/*!
    0.93
     дописавши
    0.89
     houſe
    0.89
     myſelf
    0.84
    Tembelea
    0.83
    Act Density 0.519%

    No Known Activations