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

    Neuronpedia

    INDEX
    Explanations

    references to motor vehicles and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ure
    -0.16
    mir
    -0.16
    urement
    -0.16
     SHR
    -0.15
    mare
    -0.15
    tim
    -0.15
    ming
    -0.15
    gm
    -0.15
    ego
    -0.15
    ens
    -0.15
    POSITIVE LOGITS
    ized
    0.33
    cycl
    0.30
    cade
    0.28
    ised
    0.26
    bike
    0.25
    homes
    0.25
    cycle
    0.25
    cycles
    0.24
    olla
    0.23
    home
    0.23
    Act Density 0.009%

    No Known Activations