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

    Neuronpedia

    INDEX
    Explanations

    mentions of tolls or fees

    oai_token-act-pair · gpt-3.5-turbo

    references to tolls, particularly in contexts related to costs and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itals
    -0.89
    ITY
    -0.76
     Correspond
    -0.74
    ITIES
    -0.64
    natureconservancy
    -0.64
    nces
    -0.63
    ################
    -0.63
    )=(
    -0.63
    ibilities
    -0.62
    ansion
    -0.60
    POSITIVE LOGITS
     toll
    0.90
     booth
    0.86
     booths
    0.85
     plaza
    0.79
     Dickinson
    0.78
    thirst
    0.77
    ãĤ´
    0.76
    enance
    0.75
    sin
    0.72
    son
    0.71
    Act Density 0.054%

    No Known Activations