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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ialog
    -0.16
    igest
    -0.15
    eson
    -0.14
    882
    -0.14
     twice
    -0.13
    HEMA
    -0.13
    ILLA
    -0.13
     Twice
    -0.13
    _WH
    -0.13
    ilda
    -0.13
    POSITIVE LOGITS
     definit
    0.36
     definitely
    0.35
     definite
    0.32
     certainty
    0.32
     Definitely
    0.28
     definitive
    0.27
     beyond
    0.26
    å®ļ
    0.26
     cert
    0.24
     absolute
    0.24
    Act Density 0.144%

    No Known Activations