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

    Neuronpedia

    INDEX
    Explanations

    non-English characters

    oai_token-act-pair · gpt-3.5-turbo

    Unicode characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.91
     Instr
    -0.83
    matic
    -0.78
     slic
    -0.74
     Appalach
    -0.74
    enegger
    -0.73
    milo
    -0.72
    ciating
    -0.71
    ocre
    -0.69
     accur
    -0.68
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.10
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.90
    ĺ
    0.89
    à©
    0.89
    ļ
    0.87
    Ķ
    0.87
    ishable
    0.87
    Ĺ
    0.87
    ľ
    0.86
    cffffcc
    0.84
    Act Density 0.057%

    No Known Activations