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

    Neuronpedia

    INDEX
    Explanations

    instances of significant problems or threats in various contexts

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

    after "caused" triggers

    np_acts-logits-general · gemini-2.0-flash

    causes and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.68
    balleur
    -0.52
    XtraReports
    -0.50
    MLLoader
    -0.50
    RTEE
    -0.49
     supérieurs
    -0.47
     purpoſe
    -0.47
     Савезне
    -0.47
    canestro
    -0.47
    JpaRepository
    -0.45
    POSITIVE LOGITS
     causes
    0.72
     caused
    0.67
     threats
    0.65
     threatening
    0.63
    causes
    0.62
     dangers
    0.59
     causing
    0.58
     threat
    0.56
     threaten
    0.56
     insidious
    0.55
    Act Density 1.053%

    No Known Activations