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

    Neuronpedia

    INDEX
    Explanations

    phrases that express the need for assistance or enhancement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContextHolder
    -0.16
    itten
    -0.15
    ë³ij
    -0.15
    SizeMode
    -0.15
    abal
    -0.14
     bì
    -0.14
    alles
    -0.14
    æĺĮ
    -0.14
    achs
    -0.14
    ÑĢеб
    -0.14
    POSITIVE LOGITS
     boost
    0.65
    boost
    0.50
     Boost
    0.49
     BOOST
    0.45
     boosts
    0.43
    Boost
    0.43
     injection
    0.38
    .boost
    0.38
     booster
    0.36
     boosting
    0.36
    Act Density 0.143%

    No Known Activations