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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alo
    -0.16
    ält
    -0.16
    retty
    -0.15
    EDIA
    -0.15
    ily
    -0.15
    andum
    -0.15
    uka
    -0.15
    uary
    -0.15
    remely
    -0.14
     Dispatch
    -0.14
    POSITIVE LOGITS
     nor
    0.19
     anymore
    0.18
    opes
    0.16
     until
    0.15
    nor
    0.15
     unaware
    0.15
    enschaft
    0.15
    ä¸įçŁ¥éģĵ
    0.15
    sal
    0.15
     direction
    0.14
    Act Density 0.060%

    No Known Activations