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

    Neuronpedia

    INDEX
    Explanations

    sentences that express existential questions and reflections on purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.94
     Baillargeon
    -0.74
     postIndex
    -0.69
    ⓧ
    -0.67
     unsuccessfully
    -0.64
    ？】
    -0.62
    principalColumn
    -0.61
     specified
    -0.61
    ]--;
    -0.59
    Sinon
    -0.59
    POSITIVE LOGITS
     humans
    0.62
     humanity
    0.59
     mennesker
    0.59
    hidupan
    0.58
     essentielles
    0.54
     ideas
    0.53
     mankind
    0.53
     beings
    0.53
    Kjelder
    0.52
     sensibilité
    0.52
    Act Density 0.245%

    No Known Activations