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

    Neuronpedia

    INDEX
    Explanations

    code snippets and technical text, such as commands, variables, and programming concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ioch
    -0.93
    eton
    -0.93
    wash
    -0.92
    esson
    -0.86
    imov
    -0.86
    izer
    -0.86
    isphere
    -0.84
    onom
    -0.83
    rigan
    -0.82
    ogun
    -0.82
    POSITIVE LOGITS
     1
    1.10
     2
    0.92
     5
    0.91
     10
    0.86
     15
    0.86
     scant
    0.86
     TBD
    0.82
    nown
    0.82
     6
    0.81
     7
    0.81
    Act Density 0.556%

    No Known Activations