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

    Neuronpedia

    INDEX
    Explanations

    the word "taxi"

    oai_token-act-pair · gpt-4-turbo

    specific mentions of taxi services

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of taxis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.89
    utz
    -0.88
    wart
    -0.84
    vironment
    -0.76
    isite
    -0.75
    phal
    -0.69
    warts
    -0.68
    pha
    -0.65
    hem
    -0.65
    adow
    -0.63
    POSITIVE LOGITS
     taxi
    1.11
     taxis
    0.96
     cab
    0.87
     Taxi
    0.86
     rides
    0.80
     courier
    0.79
     dispens
    0.73
     corrid
    0.71
     Lyft
    0.71
     ride
    0.70
    Act Density 0.007%

    No Known Activations