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

    Neuronpedia

    INDEX
    Explanations

    terms describing dependency in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    shades
    -0.72
    ?>">
    -0.71
    es
    -0.68
    Sach
    -0.68
    helves
    -0.67
    )_/¯
    -0.65
     sark
    -0.63
     juzg
    -0.63
     préfé
    -0.62
    paigns
    -0.62
    POSITIVE LOGITS
     Ziegler
    0.79
    uate
    0.71
    ++++++++++++++++
    0.71
     dependent
    0.71
    cmath
    0.71
     nant
    0.70
     Dependent
    0.69
     wrap
    0.69
    letal
    0.69
    yte
    0.68
    Act Density 0.004%

    No Known Activations