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

    Neuronpedia

    INDEX
    Explanations

    references to profiles within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ew
    -0.22
    oral
    -0.19
    fall
    -0.16
    ness
    -0.16
    ala
    -0.15
    uno
    -0.15
    nes
    -0.15
    our
    -0.15
    ward
    -0.15
    ali
    -0.14
    POSITIVE LOGITS
    yte
    0.18
    ácil
    0.16
    .Profile
    0.16
    enstein
    0.15
    ed
    0.15
    ston
    0.15
    ucks
    0.15
    /profile
    0.15
    AndPassword
    0.15
    eÄį
    0.15
    Act Density 0.016%

    No Known Activations