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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to inventions and advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -1.72
    <eos>
    -1.27
    ↵↵↵
    -1.05
     […]
    -0.94
    )){
    -0.93
    ↵↵↵↵
    -0.92
    ↵
    -0.89
    "]);
    -0.89
    }$.\\
    -0.89
    </strong>
    -0.88
    POSITIVE LOGITS
    ſelf
    0.96
    tvguidetime
    0.93
    ſelves
    0.88
     pleaſure
    0.85
    <bos>
    0.82
    neſs
    0.81
     raiſ
    0.78
     iſt
    0.78
    FTFY
    0.78
     VIDEOTAPE
    0.77
    Act Density 4.034%

    No Known Activations