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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate responsibility or accountability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iveau
    -0.16
    оза
    -0.15
    楽
    -0.15
    achi
    -0.15
    ycz
    -0.14
    Quiz
    -0.14
     Bene
    -0.14
    arn
    -0.14
    pole
    -0.13
    uem
    -0.13
    POSITIVE LOGITS
    inha
    0.17
    auer
    0.15
    sth
    0.15
    ENSE
    0.15
    MBER
    0.14
    ispecies
    0.14
    istik
    0.14
    zac
    0.14
    ivalence
    0.14
    ifact
    0.14
    Act Density 0.017%

    No Known Activations