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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating significant negative impacts or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.19
    595
    -0.16
    ollo
    -0.16
    eselect
    -0.16
     sá»ķ
    -0.15
    ekte
    -0.15
    goog
    -0.15
     DM
    -0.15
    095
    -0.15
    areth
    -0.15
    POSITIVE LOGITS
    mour
    0.18
     Wilhelm
    0.16
    otron
    0.14
    볨
    0.14
     Freed
    0.14
    PILE
    0.14
    rael
    0.13
    peak
    0.13
    ku
    0.13
    ogen
    0.13
    Act Density 0.001%

    No Known Activations