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

    Neuronpedia

    INDEX
    Explanations

    sequences containing the abbreviation "UB" and "OLD"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific firearm model or its features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olls
    -0.77
    itures
    -0.73
    hart
    -0.72
    igans
    -0.69
    visors
    -0.68
    eners
    -0.68
    angelo
    -0.67
    ensis
    -0.66
    heart
    -0.66
    rities
    -0.64
    POSITIVE LOGITS
    UB
    3.53
    OLD
    1.42
    UG
    1.37
    OUND
    1.31
    UR
    1.27
    URN
    1.26
    ALD
    1.26
    ULL
    1.25
    UM
    1.22
    UF
    1.21
    Act Density 0.013%

    No Known Activations