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

    Neuronpedia

    INDEX
    Explanations

    phrases that include citations or references to other people's statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rias
    -0.16
    elay
    -0.16
    onso
    -0.16
    emens
    -0.15
    REFERRED
    -0.15
    299
    -0.14
    ords
    -0.14
    uis
    -0.14
    го
    -0.14
    á»iji
    -0.14
    POSITIVE LOGITS
    anja
    0.19
    seau
    0.17
    ">//
    0.15
     fitte
    0.15
    iang
    0.15
    ÑĢеменно
    0.15
    fea
    0.14
    amber
    0.14
    Åĵur
    0.14
     coincidence
    0.14
    Act Density 0.057%

    No Known Activations