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

    Neuronpedia

    INDEX
    Explanations

    the word 'ant' and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Curve
    -0.72
     Viz
    -0.71
     Stras
    -0.69
     Plain
    -0.69
    Brand
    -0.67
     Gorge
    -0.67
     Province
    -0.67
    ONT
    -0.65
     Royale
    -0.65
    areth
    -0.64
    POSITIVE LOGITS
    iques
    1.09
    elope
    1.04
    icy
    1.02
    icycle
    1.00
    icol
    0.95
    isp
    0.94
    iculture
    0.93
    icons
    0.91
    hesis
    0.90
    iven
    0.90
    Act Density 0.016%

    No Known Activations