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

    Neuronpedia

    INDEX
    Explanations

    references to actions related to assembling or assembly plants

    oai_token-act-pair · gpt-3.5-turbo

    references to assembly plants or assembly-related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imaru
    -0.74
    ched
    -0.68
    verson
    -0.64
    fall
    -0.61
    omorphic
    -0.61
    awar
    -0.61
     hikers
    -0.60
    ears
    -0.59
    Released
    -0.59
     backpack
    -0.58
    POSITIVE LOGITS
    member
    0.99
    woman
    0.90
    atures
    0.88
    mate
    0.86
    rats
    0.86
    members
    0.86
     Speaker
    0.85
    istry
    0.84
    Assembly
    0.82
    man
    0.79
    Act Density 0.049%

    No Known Activations