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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.95
    <bos>
    -0.80
    ’
    -0.63
     CreateTagHelper
    -0.62
    Koordinaten
    -0.59
    }}}}
    -0.58
    </b>
    -0.56
     
    -0.56
     “
    -0.50
     I
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.84
     surla
    0.76
    
    0.73
     utafitiHapana
    0.73
     myſelf
    0.72
     \\
    0.71
     betweenstory
    0.70
    Clik
    0.69
     ―――――
    0.68
     Efq
    0.67
    Act Density 1.666%

    No Known Activations