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

    Neuronpedia

    INDEX
    Explanations

    sequences and patterns in code or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.67
     CreateTagHelper
    -0.63
    principalTable
    -0.46
    Géographie
    -0.46
     Larkin
    -0.46
    "
    -0.45
     Malo
    -0.45
    rungsseite
    -0.44
    inkin
    -0.44
     createSprite
    -0.44
    POSITIVE LOGITS
    ↵
    1.36
            
    0.63
    ↵↵↵
    0.60
                
    0.59
    ↵↵
    0.58
    RegressionTest
    0.54
    Personendaten
    0.54
    textTheme
    0.53
    ↵↵↵↵↵↵↵
    0.52
     TODO
    0.51
    Act Density 0.047%

    No Known Activations