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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that indicate reported speech or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.94
    %";
    -0.80
     houſe
    -0.79
     pleaſure
    -0.79
    )++;
    -0.77
    ngdoc
    -0.75
    AndEndTag
    -0.74
    NUMX
    -0.74
     purpoſe
    -0.72
     ſtre
    -0.71
    POSITIVE LOGITS
    “
    0.71
     “
    0.69
     "
    0.66
    â
    0.55
    "
    0.55
    :
    0.53
    parsedMessage
    0.52
    「
    0.50
    <blockquote>
    0.49
    <strong>
    0.49
    Act Density 0.094%

    No Known Activations