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

    Neuronpedia

    INDEX
    Explanations

    references to military actions and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    089
    -0.15
    304
    -0.15
    licted
    -0.15
    nip
    -0.14
     rating
    -0.14
     obr
    -0.13
    Åĵur
    -0.13
    245
    -0.13
    tones
    -0.13
    OGLE
    -0.13
    POSITIVE LOGITS
     cease
    0.27
     ceasefire
    0.24
     cessation
    0.23
     Confidence
    0.22
     Ce
    0.21
     cess
    0.20
     peace
    0.20
     modal
    0.20
     Geneva
    0.20
     spoilers
    0.20
    Act Density 0.059%

    No Known Activations