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

    Neuronpedia

    INDEX
    Explanations

    terms related to dual functionalities or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.17
    esel
    -0.15
    LY
    -0.15
    PLACE
    -0.15
    liness
    -0.15
    places
    -0.14
    дин
    -0.14
    yonel
    -0.14
    estone
    -0.14
    est
    -0.14
    POSITIVE LOGITS
    -purpose
    0.27
    istic
    0.24
    /tr
    0.21
    ities
    0.21
    ityEngine
    0.21
    ogy
    0.20
    -sided
    0.20
     purpose
    0.18
    .infinity
    0.18
    purpose
    0.18
    Act Density 0.011%

    No Known Activations