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

    Neuronpedia

    INDEX
    Explanations

    regular expressions and their pattern replacements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aptor
    -0.15
     γά
    -0.14
    erus
    -0.14
     Thief
    -0.14
    owe
    -0.14
    ÐļÐIJ
    -0.14
    Fore
    -0.14
     dém
    -0.13
    gio
    -0.13
     fore
    -0.13
    POSITIVE LOGITS
    entlich
    0.15
    outil
    0.15
    tres
    0.15
    ighbours
    0.14
    UGIN
    0.14
    258
    0.14
    за
    0.14
    optera
    0.14
    itest
    0.14
    zik
    0.14
    Act Density 0.071%

    No Known Activations