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

    Neuronpedia

    INDEX
    Explanations

    user interface interactions and actions related to controlling features or settings on a device

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aki
    -0.16
    nda
    -0.15
    anner
    -0.14
    uchs
    -0.14
    eward
    -0.14
    ioni
    -0.14
     fermentation
    -0.13
    _BOUND
    -0.13
    reation
    -0.13
    nea
    -0.13
    POSITIVE LOGITS
     quit
    0.17
    aye
    0.17
    -toggle
    0.16
    .toggle
    0.15
    _dbg
    0.15
    coat
    0.15
     Quit
    0.14
    hoff
    0.14
    ï¸
    0.14
    _TOGGLE
    0.14
    Act Density 0.064%

    No Known Activations