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

    Neuronpedia

    INDEX
    Explanations

    references to dining locations and food recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [sizeof
    -0.17
    PIPE
    -0.17
     airst
    -0.16
    çī©
    -0.15
    ALLE
    -0.15
    ALAR
    -0.15
    Ñĥже
    -0.14
     tyre
    -0.14
    emain
    -0.14
    çµIJ
    -0.14
    POSITIVE LOGITS
     fare
    0.20
     Line
    0.18
     omn
    0.18
     underground
    0.18
     RT
    0.17
     line
    0.17
     fares
    0.17
    bus
    0.16
     Metro
    0.15
     system
    0.15
    Act Density 0.179%

    No Known Activations