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

    Neuronpedia

    INDEX
    Explanations

    patterns related to regular expressions and URL structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.69
    -
    -0.48
    <eos>
    -0.48
    .
    -0.47
     –
    -0.46
      
    -0.45
    ,
    -0.45
     in
    -0.43
     -
    -0.43
    os
    -0.39
    POSITIVE LOGITS
     GoogleFonts
    1.02
    rungsseite
    0.99
     Efq
    0.99
    InputBorder
    0.99
     itſelf
    0.99
     .*
    0.96
    EDEFAULT
    0.96
     Jefus
    0.95
     myſelf
    0.94
     GenerationType
    0.94
    Act Density 0.243%

    No Known Activations