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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, regulations, and governance

    oai_token-act-pair · gpt-3.5-turbo

    words related to policies, themes, and various systems or frameworks in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaz
    -0.75
    izont
    -0.67
    kernel
    -0.65
    antha
    -0.64
    orman
    -0.62
    atus
    -0.62
    Joy
    -0.62
    termin
    -0.61
    ModLoader
    -0.61
    otos
    -0.60
    POSITIVE LOGITS
     alike
    1.60
     thereof
    1.03
     respectively
    0.97
     belonging
    0.90
     relating
    0.81
    hops
    0.80
     gal
    0.79
     therein
    0.78
     depending
    0.77
    hips
    0.77
    Act Density 0.295%

    No Known Activations