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

    Neuronpedia

    INDEX
    Explanations

    references to the integration of technology into different systems

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    efer
    -0.76
    thur
    -0.75
    76561
    -0.68
    rpm
    -0.68
    zzy
    -0.67
    ubis
    -0.65
    ulz
    -0.64
    etsk
    -0.64
    \\\\\\\\
    -0.63
    ark
    -0.63
    POSITIVE LOGITS
     into
    1.30
     INTO
    1.09
     Into
    1.07
     seamlessly
    1.02
    rity
    0.88
    into
    0.84
     onto
    0.82
    ment
    0.80
     elements
    0.77
    tion
    0.76
    Act Density 0.058%

    No Known Activations