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

    Neuronpedia

    INDEX
    Explanations

    references to military attacks and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombre
    -0.15
    quil
    -0.15
    æijĨ
    -0.14
    rane
    -0.14
    :view
    -0.14
    éļİ
    -0.14
    dez
    -0.13
     Mehr
    -0.13
     cal
    -0.13
    stå
    -0.13
    POSITIVE LOGITS
     targets
    0.41
     Targets
    0.35
    targets
    0.33
     target
    0.30
    Targets
    0.28
    target
    0.27
    缮æłĩ
    0.26
    Target
    0.24
    -target
    0.24
     infrastructure
    0.24
    Act Density 0.142%

    No Known Activations