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

    Neuronpedia

    INDEX
    Explanations

    mention of treaties or agreements related to peace processes

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

    agreements, negotiations, or ceasing hostilities

    np_acts-logits-general · gemini-2.0-flash

    negotiation and cessation of hostilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hayek
    -0.59
     defaultstate
    -0.56
    AxisAlignment
    -0.56
     Secund
    -0.56
     Immig
    -0.53
     للمعارف
    -0.52
     Dede
    -0.52
    ThroughAttribute
    -0.51
    ⓧ
    -0.50
     divent
    -0.50
    POSITIVE LOGITS
     talks
    0.88
     negotiators
    0.84
     negotiations
    0.82
    negoti
    0.80
    talks
    0.79
     dialogue
    0.75
     ceasefire
    0.75
     negotiator
    0.73
     négoci
    0.73
     negotiating
    0.72
    Act Density 0.172%

    No Known Activations