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

    Neuronpedia

    INDEX
    Explanations

    phrases that initiate actions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssel
    -0.17
    ughty
    -0.14
     Must
    -0.14
    .AspNet
    -0.14
    ught
    -0.14
    ocking
    -0.14
     кл
    -0.14
    олÑİ
    -0.13
    stown
    -0.13
    ocked
    -0.13
    POSITIVE LOGITS
    _go
    0.16
    reed
    0.16
    edes
    0.14
    enger
    0.14
    .go
    0.14
    LEncoder
    0.14
    arged
    0.13
    ึ
    0.13
     mour
    0.13
    alic
    0.13
    Act Density 0.028%

    No Known Activations