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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases indicating relationships or conditions

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

    without dispute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.43
    :
    -0.38
    enumi
    -0.38
    The
    -0.37
     an
    -0.37
     this
    -0.36
     
    -0.35
    This
    -0.34
      
    -0.34
     those
    -0.33
    POSITIVE LOGITS
    OCCURRED
    0.85
    iſen
    0.84
    tvguidetime
    0.81
     nakalista
    0.80
     tartalomajánló
    0.79
    iſchen
    0.79
    linawan
    0.79
    BufferException
    0.77
     Geiſt
    0.76
    ðsíða
    0.75
    Act Density 0.047%

    No Known Activations