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

    Neuronpedia

    INDEX
    Explanations

    references to morality and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    el
    -0.17
    es
    -0.16
    اÙĪرÛĮ
    -0.15
    247
    -0.15
    apo
    -0.15
    elan
    -0.15
    getMethod
    -0.15
    emo
    -0.14
     moy
    -0.14
    elder
    -0.14
    POSITIVE LOGITS
    izing
    0.23
    izin
    0.19
     fiber
    0.19
    istic
    0.19
    ize
    0.18
    ising
    0.18
    ities
    0.18
     compass
    0.17
    ized
    0.17
     Fiber
    0.17
    Act Density 0.013%

    No Known Activations