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

    Neuronpedia

    INDEX
    Explanations

    instances of threats, violence, and consequences in context

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

    phrases related to threats and consequences of criminal actions

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

    threats of violence and dire consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hoeddwyd
    -0.70
    DebuggerNonUser
    -0.56
    Hochspringen
    -0.53
     pinta
    -0.50
    agree
    -0.49
     negoci
    -0.48
     vérité
    -0.48
    yntaxException
    -0.47
    jspx
    -0.47
    getActiveSheet
    -0.47
    POSITIVE LOGITS
     death
    0.79
     condemnation
    0.73
     wrath
    0.71
    DockStyle
    0.70
     CreateTagHelper
    0.67
    death
    0.65
     doom
    0.64
     violence
    0.63
     ire
    0.63
    TintMode
    0.59
    Act Density 0.139%

    No Known Activations