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

    Neuronpedia

    INDEX
    Explanations

    words related to doubting and challenging beliefs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of doubt or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.78
    ISTER
    -0.77
    ullivan
    -0.70
    ALE
    -0.70
    Interstitial
    -0.68
    Discussion
    -0.64
    ixture
    -0.64
    WP
    -0.63
     Mutual
    -0.63
    Accessory
    -0.61
    POSITIVE LOGITS
     doub
    1.18
    ting
    0.91
    thood
    0.88
    staking
    0.88
    ly
    0.85
     doubted
    0.85
    ters
    0.82
    bolt
    0.80
    iably
    0.80
     nodd
    0.79
    Act Density 0.006%

    No Known Activations