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

    Neuronpedia

    INDEX
    Explanations

    terms related to copying and pasting text or code

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hips
    -0.50
    ysis
    -0.42
     Brach
    -0.42
    åŃIJ
    -0.42
    vae
    -0.40
    iott
    -0.40
     Donation
    -0.40
    iosity
    -0.40
     GOODMAN
    -0.39
     Hung
    -0.38
    POSITIVE LOGITS
    urized
    0.87
    ur
    0.59
     paste
    0.57
    lete
    0.52
    ures
    0.49
    ón
    0.45
    ured
    0.45
    ure
    0.44
    ography
    0.44
    ener
    0.44
    Act Density 0.987%

    No Known Activations