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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict and political tension

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

    potential negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chham
    -0.53
     IBOutlet
    -0.49
    OGND
    -0.49
     Wicidata
    -0.48
    fjspx
    -0.45
    katapos
    -0.43
     &___
    -0.43
    roblast
    -0.43
    makedirs
    -0.43
    segno
    -0.42
    POSITIVE LOGITS
     someday
    0.50
    addPreferredGap
    0.47
     künftig
    0.43
    addGap
    0.42
     or
    0.41
    ьаж
    0.40
     třeba
    0.40
     worse
    0.39
    voorbeeld
    0.39
     nantinya
    0.39
    Act Density 0.092%

    No Known Activations