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

    Neuronpedia

    INDEX
    Explanations

    references to primary sources

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    INESS
    -0.91
    estern
    -0.89
    OTO
    -0.78
    EEK
    -0.77
    ARDS
    -0.77
     Doodle
    -0.76
    uge
    -0.76
    orse
    -0.75
    sung
    -0.74
    UGE
    -0.73
    POSITIVE LOGITS
    tenance
    0.98
     careg
    0.95
     antagonist
    0.94
    stay
    0.90
     objective
    0.87
     pivot
    0.85
     distingu
    0.84
    ities
    0.84
     distinguishing
    0.82
    ignment
    0.81
    Act Density 5.700%

    No Known Activations