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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons and contrasts in contexts such as housing and environmental data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.65
     الحره
    -0.49
    ⓧ
    -0.49
     GenerationType
    -0.46
    دانشنامهٔ
    -0.45
    AddHtmlAttribute
    -0.45
    ArgumentParser
    -0.44
     Infórmanos
    -0.44
    fromnode
    -0.44
     rotu
    -0.44
    POSITIVE LOGITS
     predominance
    0.82
     emphasis
    0.75
     dominance
    0.71
     Emphasis
    0.69
     énfasis
    0.68
    emphasis
    0.64
     prioritizing
    0.63
     predominantly
    0.63
    Emphasis
    0.63
     preponderance
    0.62
    Act Density 0.814%

    No Known Activations