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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming concepts and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eln
    -0.17
    nal
    -0.16
    گر
    -0.15
    istrovstvÃŃ
    -0.15
    bers
    -0.15
    holes
    -0.15
    hole
    -0.14
    atron
    -0.14
    uales
    -0.14
    /xhtml
    -0.14
    POSITIVE LOGITS
    mente
    0.25
    ities
    0.25
    ness
    0.24
    NESS
    0.21
    ity
    0.20
    gado
    0.18
    zza
    0.18
    most
    0.17
    idad
    0.16
    -handed
    0.16
    Act Density 0.719%

    No Known Activations