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

    Neuronpedia

    INDEX
    Explanations

    terms related to behavioral conditioning and training methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.52
     autorytatywna
    -0.52
    hyrchwyd
    -0.47
    PropertyChanging
    -0.46
     تعدى
    -0.46
     disambiguazione
    -0.45
    Демографія
    -0.45
     Roskov
    -0.44
    énario
    -0.44
    portál
    -0.44
    POSITIVE LOGITS
    DIPSETTING
    0.41
     reinforcement
    0.40
     lenker
    0.39
    !*\
    0.38
     reward
    0.38
     Reinforcement
    0.37
    WireFormatLite
    0.37
     récompense
    0.36
    pulumi
    0.36
    reward
    0.35
    Act Density 0.412%

    No Known Activations