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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal preferences and viewpoints

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    grounds
    -0.99
     Gork
    -0.96
    riots
    -0.95
     awaits
    -0.94
    river
    -0.94
    ARDIS
    -0.94
    proof
    -0.93
    hes
    -0.93
    soDeliveryDate
    -0.93
    abiding
    -0.92
    POSITIVE LOGITS
     minimize
    1.39
    asty
    1.36
     keep
    1.34
     encourage
    1.34
     pretend
    1.33
     remind
    1.32
     avoid
    1.29
     emulate
    1.28
     celebrate
    1.28
     see
    1.27
    Act Density 0.730%

    No Known Activations