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

    Neuronpedia

    INDEX
    Explanations

    terminology related to uniqueness or differentiation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    '}>
    -1.02
     ***/
    -0.96
     Horv
    -0.92
    ंदीखरीदारी
    -0.88
    ]-->
    -0.88
    monary
    -0.86
    <()>
    -0.85
     tartalomajánló
    -0.85
    rehensive
    -0.84
    --]
    -0.84
    POSITIVE LOGITS
    INCT
    0.81
    ness
    0.77
     tortas
    0.61
    next
    0.58
    odacty
    0.58
    :✨
    0.57
    inct
    0.56
     Eis
    0.56
     Jay
    0.56
     Jays
    0.56
    Act Density 0.005%

    No Known Activations