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

    Neuronpedia

    INDEX
    Explanations

    structured data elements and their attributes in a JSON-like format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     T
    -0.80
     
    -0.76
     p
    -0.72
     I
    -0.72
     The
    -0.70
     To
    -0.70
     In
    -0.69
     P
    -0.68
     N
    -0.67
     .
    -0.67
    POSITIVE LOGITS
     itſelf
    1.30
     myſelf
    1.28
     فريبيس
    1.22
    ValueStyle
    1.17
     doubtnut
    1.17
     Monfieur
    1.17
     themſelves
    1.12
     ་་
    1.12
     Roskov
    1.12
     Efq
    1.10
    Act Density 0.139%

    No Known Activations