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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to legal claims and allegations

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

    Preceding pronouns followed by verbs indicating harm

    np_acts-logits-general · gemini-2.0-flash

    subject relied on assurances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     felic
    -0.32
     lazy
    -0.31
     kav
    -0.31
    陋
    -0.31
    Converters
    -0.30
     admission
    -0.30
     avar
    -0.29
     eu
    -0.29
     ev
    -0.28
     tap
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.91
     suffers
    0.78
     suffer
    0.73
     suffered
    0.71
    __*/
    0.70
     sufre
    0.69
     suffering
    0.69
     PeEnEo
    0.68
     sufri
    0.67
    principalColumn
    0.66
    Act Density 0.580%

    No Known Activations