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

    Neuronpedia

    INDEX
    Explanations

    references to programming structures and operations typically seen in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \_
    -0.67
    )_
    -0.61
    ]_
    -0.57
     _
    -0.56
    __
    -0.53
    ._
    -0.52
    ~
    -0.49
    Ignoring
    -0.49
    ___
    -0.49
    ِ
    -0.48
    POSITIVE LOGITS
    //{
    0.67
    }*/
    0.67
    "],
    0.65
     >=",
    0.65
    ”!
    0.64
    +#+
    0.63
    CodedInputStream
    0.63
    "]);
    0.61
    ">{{$
    0.61
     …”
    0.61
    Act Density 0.391%

    No Known Activations