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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "remarks" as well as associated commentary or feedback

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

    remarks about following statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onOptions
    -0.53
    Opti
    -0.52
     Diony
    -0.52
    cupertino
    -0.51
     Solver
    -0.50
     Installer
    -0.50
    CYP
    -0.50
    generators
    -0.49
    Solver
    -0.49
     ſind
    -0.48
    POSITIVE LOGITS
     remarks
    1.87
     Remarks
    1.53
    Remarks
    1.45
    remarks
    1.42
     REMARKS
    1.41
     remark
    1.19
    REMARKS
    1.09
     remarked
    1.03
     Bemerkungen
    0.91
     comments
    0.82
    Act Density 0.003%

    No Known Activations