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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical definitions and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.07
     itſelf
    -0.97
     themſelves
    -0.92
     himſelf
    -0.79
     Theſe
    -0.77
    rungsseite
    -0.74
     ―――――
    -0.73
     theſe
    -0.73
     $_"
    -0.72
     Anſ
    -0.72
    POSITIVE LOGITS
    IntoConstraints
    0.74
     to
    0.47
    yarnpkg
    0.44
     الرياضيه
    0.43
     okuyayım
    0.43
    <bos>
    0.42
     [
    0.42
     
    0.42
     دیکھیے
    0.41
     be
    0.41
    Act Density 2.041%

    No Known Activations