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

    Neuronpedia

    INDEX
    Explanations

    phrases related to subjective experiences and narratives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.85
    ETS
    -0.73
    âĺ
    -0.72
    REE
    -0.70
    cause
    -0.70
    quote
    -0.69
    æ©
    -0.67
    JV
    -0.67
    UME
    -0.66
     ALSO
    -0.66
    POSITIVE LOGITS
     exhaustive
    0.97
     unsuccessful
    0.95
     hiatus
    0.94
     hesitation
    0.93
     exhausting
    0.92
     stint
    0.92
     iterations
    0.87
     initial
    0.85
     consultation
    0.85
     gru
    0.84
    Act Density 0.115%

    No Known Activations