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

    Neuronpedia

    INDEX
    Explanations

    references to prominent historical figures and events related to war and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رشف
    -0.68
     للمعارف
    -0.60
    achusetts
    -0.48
     Insee
    -0.48
     חיצוניים
    -0.48
    DebuggerNonUser
    -0.47
     defaultstate
    -0.45
    pektor
    -0.45
    endenza
    -0.43
     Benef
    -0.43
    POSITIVE LOGITS
     captive
    1.40
     captured
    1.34
     hostage
    1.29
     captives
    1.27
     captivity
    1.26
     hostages
    1.18
     prisoner
    1.16
     prisoners
    1.09
     capture
    1.06
     kidnapped
    1.04
    Act Density 0.186%

    No Known Activations