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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or items being discussed or analyzed

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.99
    ScopeManager
    -0.97
    Personendaten
    -0.92
    tiérrez
    -0.89
    ]$}
    -0.87
    %\]
    -0.86
    Autoritní
    -0.85
    Liefs
    -0.84
     ligiloj
    -0.84
    amaño
    -0.83
    POSITIVE LOGITS
    .
    0.57
    I
    0.52
    se
    0.51
    Is
    0.50
    A
    0.50
    a
    0.49
    <i>
    0.49
    Se
    0.49
    ,
    0.49
     -
    0.48
    Act Density 0.018%

    No Known Activations