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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concluding events or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens indicating conclusion or end

    np_acts-logits-general · gemini-2.0-flash

    ends and conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.72
     mergeFrom
    -0.70
     ujednoznacz
    -0.69
    ніципалі
    -0.66
    GeneratedCode
    -0.65
    ="@+
    -0.63
     AssemblyTitle
    -0.62
     noqa
    -0.61
    rawDesc
    -0.61
    StructEnd
    -0.60
    POSITIVE LOGITS
     note
    0.88
    Note
    0.73
    note
    0.71
     Note
    0.69
     catatan
    0.57
     notes
    0.55
     noter
    0.55
     bang
    0.55
     abruptly
    0.53
     noting
    0.53
    Act Density 0.115%

    No Known Activations