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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks and sentence beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -1.84
    ↵
    -1.10
    ↵↵↵
    -1.09
    </h3>
    -0.93
    ↵↵↵↵
    -0.81
    ↵↵↵↵↵
    -0.80
    </h4>
    -0.77
    <eos>
    -0.75
    </blockquote>
    -0.74
    ↵↵↵↵↵↵↵
    -0.73
    POSITIVE LOGITS
     كومونز
    0.76
    GraphicsUnit
    0.71
    Vidite
    0.67
     newBuilder
    0.62
    TextAppearance
    0.61
    nmgp
    0.60
    umenical
    0.60
    copg
    0.58
    eneuve
    0.58
    HostException
    0.57
    Act Density 0.558%

    No Known Activations