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

    Neuronpedia

    INDEX
    Explanations

    structured data patterns or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]-->
    -0.64
    Filmografie
    -0.57
    estries
    -0.56
    الثة
    -0.56
    paksa
    -0.54
     homoto
    -0.53
     joka
    -0.52
     Kearney
    -0.52
     Brack
    -0.52
     воскрес
    -0.50
    POSITIVE LOGITS
    abc
    0.90
     ABC
    0.89
     abc
    0.86
    ABC
    0.78
    qrstuvwxyz
    0.72
    abcd
    0.69
    xyz
    0.67
    ABCDEF
    0.67
     xyz
    0.64
    XYZ
    0.63
    Act Density 0.411%

    No Known Activations