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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate confusion or inquire about information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.88
    </strong>
    -0.80
    <eos>
    -0.80
    setViewportView
    -0.71
    下载附件
    -0.67
    ).}
    -0.66
    }>
    -0.66
    unknownFields
    -0.65
    )}.
    -0.64
    حوالہ
    -0.64
    POSITIVE LOGITS
    <bos>
    1.03
     betweenstory
    0.71
     resourceCulture
    0.61
     Савезне
    0.53
     podjela
    0.50
    SharedCtor
    0.49
    Diwedd
    0.49
    UVWXYZ
    0.47
    InjectAttribute
    0.46
     DialogInterface
    0.44
    Act Density 2.808%

    No Known Activations