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

    Neuronpedia

    INDEX
    Explanations

    references to tensor attributes and related error messages in programming contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.58
    Eksteraj
    -0.52
     d
    -0.50
    <eos>
    -0.48
     bristle
    -0.45
    che
    -0.45
     
    -0.45
     tipping
    -0.44
     v
    -0.44
    ToolStrip
    -0.43
    POSITIVE LOGITS
    ]--;
    0.82
     bezeichneter
    0.78
     ―――――
    0.74
    Autoritní
    0.71
     itſelf
    0.70
     ſtate
    0.68
    verwijspagina
    0.68
     AspNetCore
    0.67
     auffi
    0.65
    ibol
    0.65
    Act Density 0.025%

    No Known Activations