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

    Neuronpedia

    INDEX
    Explanations

    terms related to engagement and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -Sah
    -0.18
    swire
    -0.17
    chod
    -0.17
    omial
    -0.16
    ahoma
    -0.15
    chu
    -0.15
    iggins
    -0.14
    venir
    -0.14
    /server
    -0.14
    ray
    -0.14
    POSITIVE LOGITS
    /disable
    0.19
    /dis
    0.19
    ments
    0.18
    eng
    0.18
     engagement
    0.18
    gi
    0.17
    agement
    0.17
    ment
    0.17
    hart
    0.16
    Eng
    0.15
    Act Density 0.026%

    No Known Activations