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

    Neuronpedia

    INDEX
    Explanations

    phrases related to peace agreements or truces

    oai_token-act-pair · gpt-3.5-turbo

    references to ceasefires and truces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Leary
    -0.82
    Lear
    -0.81
    Magikarp
    -0.81
    apore
    -0.72
    ulz
    -0.71
    race
    -0.71
    yon
    -0.70
    iris
    -0.70
    alph
    -0.70
     Printed
    -0.70
    POSITIVE LOGITS
     ceasefire
    1.28
     truce
    1.22
     treaty
    0.92
     treaties
    0.90
    ascus
    0.84
     agreements
    0.82
     agreement
    0.82
     peacefully
    0.81
    ilitation
    0.80
    escal
    0.80
    Act Density 0.022%

    No Known Activations