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

    Neuronpedia

    INDEX
    Explanations

    references to autograph signing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    forth
    -0.71
    lihood
    -0.69
    nesday
    -0.64
     harness
    -0.63
     Penet
    -0.60
     VI
    -0.60
     Forbidden
    -0.58
     Continued
    -0.58
    imaru
    -0.56
     Sutton
    -0.56
    POSITIVE LOGITS
    ographs
    1.48
    opsy
    1.44
    ograph
    1.43
    umn
    1.42
    onomous
    1.42
    ographed
    1.34
    onomy
    1.32
    obi
    1.27
    ocom
    1.25
    ograp
    1.23
    Act Density 0.024%

    No Known Activations