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

    Neuronpedia

    INDEX
    Explanations

    XML tags and related attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     möchtest
    -0.31
    '
    -0.31
     dieselbe
    -0.28
    utilisons
    -0.27
     pungkas
    -0.26
     līdz
    -0.26
     auroit
    -0.25
     puissiez
    -0.25
     similaires
    -0.25
     transferred
    -0.25
    POSITIVE LOGITS
    <unused79>
    0.96
    <unused74>
    0.95
    <unused41>
    0.95
    <unused42>
    0.95
    <unused80>
    0.95
    <unused23>
    0.95
    <unused43>
    0.95
    <unused47>
    0.95
    [@BOS@]
    0.94
    <unused8>
    0.94
    Act Density 0.964%

    No Known Activations