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

    Neuronpedia

    INDEX
    Explanations

    elements related to community initiatives, projects, and collaborative efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itled
    -0.20
    Called
    -0.18
     Called
    -0.18
     titled
    -0.17
     entitled
    -0.16
     such
    -0.16
    avers
    -0.15
     termed
    -0.15
     titul
    -0.14
    such
    -0.14
    POSITIVE LOGITS
     originally
    0.17
    ette
    0.17
     developed
    0.16
     cum
    0.16
     ideal
    0.16
     similar
    0.15
     based
    0.15
    orro
    0.15
    that
    0.15
     created
    0.15
    Act Density 0.266%

    No Known Activations