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

    Neuronpedia

    INDEX
    Explanations

    references to protected classes or group membership in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herzog
    -0.54
    ')],
    -0.53
    ]^{-
    -0.53
     }}}{
    -0.51
    ']):
    -0.50
    '])->
    -0.49
    ')}}">
    -0.48
     metter
    -0.47
    '));
    -0.47
    ]]:
    -0.46
    POSITIVE LOGITS
     ProtoMessage
    0.84
    MLLoader
    0.83
    migrationBuilder
    0.73
    ArgsConstructor
    0.72
    ไหน
    0.70
     cherchés
    0.69
     transfieras
    0.68
    expandindo
    0.68
     estekak
    0.67
    bewerken
    0.66
    Act Density 0.304%

    No Known Activations