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

    Neuronpedia

    INDEX
    Explanations

    references to vehicle components and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilos
    -0.17
     Tiles
    -0.15
    villa
    -0.15
    út
    -0.15
    inyin
    -0.15
    ilig
    -0.15
    ppard
    -0.15
     tonic
    -0.14
    025
    -0.13
    felt
    -0.13
    POSITIVE LOGITS
     hal
    0.25
     ta
    0.24
     fog
    0.24
     Xen
    0.23
     Fog
    0.23
     lenses
    0.22
     Hal
    0.22
     xen
    0.22
     head
    0.22
     tail
    0.21
    Act Density 0.012%

    No Known Activations