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

    Neuronpedia

    INDEX
    Explanations

    references to moral or ethical teachings and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ı
    -0.17
    ê
    -0.16
    orc
    -0.15
    hea
    -0.15
     fat
    -0.14
    rew
    -0.14
    oth
    -0.14
    ouser
    -0.14
    ":[{↵
    -0.14
     Warren
    -0.14
    POSITIVE LOGITS
    udit
    0.15
    ud
    0.15
    wards
    0.14
    parator
    0.14
     Artificial
    0.14
     Dahl
    0.14
    EMENT
    0.14
    ÙĪÙĨد
    0.14
    UX
    0.14
     artificial
    0.14
    Act Density 0.148%

    No Known Activations