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

    Neuronpedia

    INDEX
    Explanations

    elements related to user-centered design and efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amus
    -0.15
    ijo
    -0.14
    iri
    -0.14
    ija
    -0.13
    kou
    -0.13
    \Abstract
    -0.13
    asbourg
    -0.13
    erry
    -0.13
    oney
    -0.13
    yh
    -0.13
    POSITIVE LOGITS
     Bols
    0.15
    ente
    0.14
    ç§
    0.14
     Jewel
    0.14
    haled
    0.14
    eworld
    0.14
    _INTR
    0.13
    esub
    0.13
    antt
    0.13
    ape
    0.13
    Act Density 0.071%

    No Known Activations