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

    Neuronpedia

    INDEX
    Explanations

    conversations and protocols related to medical or clinical trial participant monitoring and adverse event reporting

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

    Following certain nouns/pronouns

    np_acts-logits-general · gemini-2.0-flash

    subject followed by state of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tentu
    -0.61
    woordig
    -0.58
     spesso
    -0.57
    often
    -0.54
     souvent
    -0.54
     gjerne
    -0.53
     often
    -0.53
    Much
    -0.52
    EndInit
    -0.52
    følgelig
    -0.51
    POSITIVE LOGITS
     exceeds
    0.81
     unexpectedly
    0.80
     otherwise
    0.76
    Personendaten
    0.76
    你觉得
    0.73
    それとも
    0.71
     blijkt
    0.67
     OTHERWISE
    0.67
     exceed
    0.66
     or
    0.66
    Act Density 1.051%

    No Known Activations