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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and data structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensement
    -0.87
     محفوظة
    -0.84
     ProtoMessage
    -0.81
     actionMode
    -0.77
    featureID
    -0.76
    XmlAccessType
    -0.74
    GEBURTSDATUM
    -0.73
    énario
    -0.72
    MockBean
    -0.70
    AsUp
    -0.69
    POSITIVE LOGITS
    <eos>
    0.61
    findpost
    0.55
    そして
    0.52
    <tr>
    0.51
    […]
    0.49
    

    0.47
    ↵↵
    0.47
    gemäß
    0.46
     resulting
    0.46
    ${\
    0.45
    Act Density 0.312%

    No Known Activations