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

    Neuronpedia

    INDEX
    Explanations

    terms related to legality and appropriateness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zijne
    -0.32
     super
    -0.30
     verster
    -0.29
     hjär
    -0.29
     []);
    -0.29
     full
    -0.29
     īpa
    -0.28
     malattie
    -0.28
     fapt
    -0.28
     lanterna
    -0.28
    POSITIVE LOGITS
     acceptable
    0.86
     Acceptable
    0.84
    Acceptable
    0.82
     '\\;'
    0.82
    richTextPanel
    0.77
     suitable
    0.77
    Appropriate
    0.76
    acceptable
    0.75
     Appropriate
    0.74
    Suitable
    0.74
    Act Density 0.585%

    No Known Activations