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

    Neuronpedia

    INDEX
    Explanations

    references to code syntax features related to paths or sequences in diagrams

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.73
     iſt
    -0.70
     دیکھیے
    -0.69
    šanai
    -0.67
     myſelf
    -0.65
     houſe
    -0.63
     itſelf
    -0.63
    ſelf
    -0.63
     فريبيس
    -0.63
     purpoſe
    -0.63
    POSITIVE LOGITS
    paths
    1.77
     paths
    1.62
     Paths
    1.47
    Paths
    1.34
     compagn
    0.66
     chemins
    0.62
     caminos
    0.60
     Appl
    0.54
     Pardo
    0.54
     Wege
    0.54
    Act Density 0.001%

    No Known Activations