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

    Neuronpedia

    INDEX
    Explanations

    phrases related to procedural instructions and processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.45
    orda
    -0.42
     “
    -0.41
     Bo
    -0.41
     De
    -0.40
    ↵
    -0.40
     infine
    -0.39
    res
    -0.39
     or
    -0.37
    me
    -0.37
    POSITIVE LOGITS
     itſelf
    1.04
     myſelf
    0.93
    :✨
    0.88
    MethodManager
    0.85
    AsUp
    0.85
     automatiquement
    0.83
     hObject
    0.82
     auffi
    0.81
    SourceChecksum
    0.81
     Monfieur
    0.81
    Act Density 0.116%

    No Known Activations