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

    Neuronpedia

    INDEX
    Explanations

    sequences related to formal introductions or polite communication

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

    introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hå
    -0.42
     Vermögen
    -0.35
     Unsc
    -0.35
     médié
    -0.34
     förr
    -0.32
     ciné
    -0.32
     ivelany
    -0.32
    ésult
    -0.32
     Wherefore
    -0.31
    piram
    -0.31
    POSITIVE LOGITS
    AndEndTag
    0.66
    httphttps
    0.65
    fjspx
    0.64
    دانشنامهٔ
    0.63
     simplifié
    0.62
    GOTREF
    0.61
    ftagPool
    0.59
    ValueStyle
    0.56
    SharedCtor
    0.55
     насељу
    0.55
    Act Density 0.034%

    No Known Activations