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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Be" indicating instructions or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    the word "Be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glide
    -0.67
     drift
    -0.65
     resonance
    -0.65
     Relief
    -0.64
     Comet
    -0.64
     pole
    -0.64
     lapse
    -0.63
     procedure
    -0.63
     tape
    -0.62
     firsthand
    -0.61
    POSITIVE LOGITS
    arers
    1.20
    yond
    1.18
    aum
    1.15
    acons
    1.13
    hemoth
    1.13
    ijing
    1.06
    arer
    1.05
    ards
    1.03
    friends
    1.02
    ech
    0.99
    Act Density 0.025%

    No Known Activations