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

    Neuronpedia

    INDEX
    Explanations

    phrasing related to experiences and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahl
    -0.07
    uÃŃ
    -0.07
    ụn
    -0.07
    imenti
    -0.07
    TouchUpInside
    -0.07
    esktop
    -0.07
    ahn
    -0.07
    uckles
    -0.06
    onders
    -0.06
    uala
    -0.06
    POSITIVE LOGITS
    .Pool
    0.06
    isha
    0.06
    alt
    0.06
    DOM
    0.06
    شاÙĨ
    0.06
    оÑĢд
    0.06
    built
    0.06
    ải
    0.06
    λια
    0.06
     epis
    0.06
    Act Density 0.072%

    No Known Activations