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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speculation or conjecture

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "simulate" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LAT
    -0.62
     griev
    -0.61
    çĭ
    -0.56
     brand
    -0.56
    XX
    -0.55
    dain
    -0.55
    arma
    -0.54
     cost
    -0.54
    Brand
    -0.54
     unfocusedRange
    -0.54
    POSITIVE LOGITS
    ulating
    4.19
    ulates
    3.58
    ulated
    3.53
    ulate
    3.29
    ulators
    3.26
    ulation
    3.21
    ulator
    3.09
    ulations
    3.07
    ulatory
    2.94
    ulative
    2.50
    Act Density 0.018%

    No Known Activations