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

    Neuronpedia

    INDEX
    Explanations

    references to giving or receiving credit in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cakes
    -0.17
    aterno
    -0.16
    thood
    -0.16
    cab
    -0.16
    .Expressions
    -0.16
    Cipher
    -0.15
    ocale
    -0.14
    éĻĪ
    -0.14
    ÑĸллÑı
    -0.14
    \Php
    -0.14
    POSITIVE LOGITS
     credit
    1.29
     Credit
    1.13
    credit
    1.09
    Credit
    1.02
     credits
    1.01
     Credits
    0.89
    _credit
    0.87
     créd
    0.85
    .credit
    0.84
    credits
    0.79
    Act Density 0.160%

    No Known Activations