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

    Neuronpedia

    INDEX
    Explanations

    code related to file handling and data processing in CSV format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ########.
    -0.56
    InjectAttribute
    -0.52
    tagHelperRunner
    -0.50
    orghini
    -0.49
    diq
    -0.48
    搖
    -0.47
    bus
    -0.46
    ropical
    -0.45
    ThroughAttribute
    -0.44
    InputBorder
    -0.44
    POSITIVE LOGITS
     itſelf
    0.80
     Jefus
    0.79
     myſelf
    0.75
     تضيفلها
    0.74
     purpoſe
    0.70
     Monfieur
    0.70
     themſelves
    0.69
     ſche
    0.69
     Theſe
    0.69
     iſt
    0.68
    Act Density 0.067%

    No Known Activations