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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or scientific concepts related to analysis and confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.73
    ázaro
    -0.72
     onCreate
    -0.71
     nav
    -0.70
     FetchType
    -0.66
    otheses
    -0.65
     елның
    -0.64
    PreferredItem
    -0.63
     GoogleFonts
    -0.63
    δες
    -0.63
    POSITIVE LOGITS
    ↵
    1.06
    ↵↵
    0.88
    [toxicity=0]
    0.77
    </tr>
    0.76
    0.73
    　　
    0.72
        
    0.71
    <h3>
    0.69
    <td>
    0.69
     rağmen
    0.68
    Act Density 0.005%

    No Known Activations