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

    Neuronpedia

    INDEX
    Explanations

    terms related to guests and attendance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abeth
    -0.19
    sten
    -0.16
    thal
    -0.16
    jang
    -0.16
    oes
    -0.15
    REW
    -0.15
    thur
    -0.15
    tring
    -0.15
    oplast
    -0.15
    zes
    -0.15
    POSITIVE LOGITS
    orado
    0.18
    /client
    0.18
    551
    0.18
    rop
    0.18
    enville
    0.17
    chaft
    0.16
    wahl
    0.16
    kü
    0.16
    marshal
    0.15
    guest
    0.14
    Act Density 0.021%

    No Known Activations