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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and sentence starters

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

    Transitioning or digressing phrases

    np_acts-logits-general · gemini-2.0-flash

    transitioning discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -1.23
    الحياه
    -0.81
    Билгалдахарш
    -0.81
    AndEndTag
    -0.78
     Roskov
    -0.77
    writeFieldEnd
    -0.76
    NameInMap
    -0.75
    principalColumn
    -0.74
    ftagPool
    -0.73
    IContainer
    -0.73
    POSITIVE LOGITS
     back
    1.06
     digress
    1.02
    回到
    0.91
    Back
    0.81
    back
    0.79
     Back
    0.78
    Returning
    0.78
     Moving
    0.78
    話が
    0.77
    に戻
    0.76
    Act Density 0.255%

    No Known Activations