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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing personal reactions and emotions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Equality
    -0.66
     slips
    -0.65
     Pastebin
    -0.62
     Ministry
    -0.60
     Initi
    -0.59
     Cover
    -0.58
     Policies
    -0.55
    clusive
    -0.54
     Hail
    -0.54
    illary
    -0.53
    POSITIVE LOGITS
     greatly
    1.08
     immensely
    0.96
     enormously
    0.95
     profoundly
    0.94
     personally
    0.90
     tremendously
    0.89
     dearly
    0.89
     deeply
    0.88
     irresist
    0.88
     psychologically
    0.84
    Act Density 0.150%

    No Known Activations