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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or judicial proceedings

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

    Followed by "that" after reporting or observation

    np_acts-logits-general · gemini-2.0-flash

    pointing out when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.71
     beſch
    -0.69
     queſta
    -0.69
    extAlignment
    -0.69
     gyhoeddwyd
    -0.68
     geſch
    -0.68
     дописавши
    -0.67
    majánló
    -0.67
    ſcher
    -0.66
    uxxxx
    -0.66
    POSITIVE LOGITS
     that
    1.08
     bahwa
    0.52
     how
    0.45
    ว่า
    0.37
     bahawa
    0.35
     why
    0.34
     faptul
    0.34
     πως
    0.33
     أنه
    0.32
     rằng
    0.32
    Act Density 0.698%

    No Known Activations