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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to medical conditions and treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.69
    ंदीखरीदारी
    -0.68
    Parcelize
    -0.65
     gyhoeddwyd
    -0.62
    Affirmed
    -0.60
    ardoor
    -0.60
    tableFuture
    -0.59
    הערות
    -0.58
    divia
    -0.57
    ))));
    -0.57
    POSITIVE LOGITS
    enumi
    0.93
    enumii
    0.72
    IDA
    0.63
    ides
    0.61
    IDES
    0.61
    Disposal
    0.59
     dispose
    0.59
     gradient
    0.58
    ida
    0.56
    gradient
    0.56
    Act Density 2.010%

    No Known Activations