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

    Neuronpedia

    INDEX
    Explanations

    quoted strings or comments within code blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    polator
    -0.16
     Slut
    -0.16
    è¨İ
    -0.15
    ÑĢÑĮ
    -0.15
    ldkf
    -0.15
    rug
    -0.15
     Cher
    -0.14
    बल
    -0.14
    HEST
    -0.14
    veloper
    -0.14
    POSITIVE LOGITS
    æ·
    0.17
    lemn
    0.16
    otron
    0.15
    è¾
    0.14
    ourd
    0.14
    otor
    0.14
    åIJĽ
    0.14
    oard
    0.14
     redis
    0.13
    aurus
    0.13
    Act Density 0.009%

    No Known Activations