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

    Neuronpedia

    INDEX
    Explanations

    phrases that include questions or expressions of uncertainty regarding actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thus
    -0.18
    æѤ
    -0.18
     while
    -0.18
     Thus
    -0.18
     thus
    -0.17
    uya
    -0.17
     Indeed
    -0.16
     BELOW
    -0.16
     whilst
    -0.15
     below
    -0.15
    POSITIVE LOGITS
     basically
    0.19
     everybody
    0.17
     Number
    0.17
     number
    0.17
    bas
    0.16
     somebody
    0.16
    Number
    0.16
    [ch
    0.16
     definitely
    0.16
     obviously
    0.16
    Act Density 0.236%

    No Known Activations