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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a high or significant quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eras
    -0.17
    uality
    -0.16
    eros
    -0.16
    eron
    -0.15
    places
    -0.15
    oa
    -0.14
    imir
    -0.14
    jin
    -0.14
    ling
    -0.14
    cken
    -0.14
    POSITIVE LOGITS
    itness
    0.17
    warts
    0.16
    /out
    0.14
    jÅ¡ÃŃ
    0.14
    vrier
    0.14
    293
    0.14
    -the
    0.14
    tal
    0.14
    coat
    0.14
     esac
    0.14
    Act Density 0.023%

    No Known Activations