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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal authorities or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -1.06
    findpost
    -1.00
    IntoConstraints
    -0.97
    <unused68>
    -0.93
    <unused52>
    -0.93
    <unused28>
    -0.92
     zwiſchen
    -0.92
    <unused8>
    -0.92
    <unused41>
    -0.92
    [@BOS@]
    -0.91
    POSITIVE LOGITS
     gen
    0.46
     sailing
    0.43
    .
    0.41
    ви
    0.39
    gen
    0.39
     reach
    0.38
    ,
    0.38
    1
    0.37
    ها
    0.37
     sail
    0.37
    Act Density 0.245%

    No Known Activations