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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and details related to computer hardware components

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    >[
    -0.54
    )."
    -0.53
     chem
    -0.48
    }.
    -0.47
     antidepressants
    -0.46
    ]."
    -0.45
     ecstasy
    -0.45
     redundancy
    -0.43
     inev
    -0.43
     aspirin
    -0.43
    POSITIVE LOGITS
    bernatorial
    0.58
    ertodd
    0.54
     consists
    0.53
     belongs
    0.52
     contains
    0.52
    brids
    0.51
     differs
    0.50
     MFT
    0.49
    iens
    0.48
    gdala
    0.47
    Act Density 24.548%

    No Known Activations