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

    Neuronpedia

    INDEX
    Explanations

    questions presenting binary choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ("$.
    -0.60
    XmlAccessorType
    -0.57
    <bos>
    -0.56
    ="{{$
    -0.54
    contentLoaded
    -0.53
     dobles
    -0.52
     समीक्षक
    -0.51
    })}\
    -0.51
    клопе
    -0.51
    ){$
    -0.51
    POSITIVE LOGITS
    LOAT
    0.75
    Pyx
    0.67
     AttributeSet
    0.66
     становника
    0.65
     circons
    0.61
    outchouc
    0.60
    MarshalTo
    0.60
    ardless
    0.60
    derry
    0.59
     Bowers
    0.59
    Act Density 0.075%

    No Known Activations