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

    Neuronpedia

    INDEX
    Explanations

    references to or mentions of taxi cabs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cab" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velength
    -0.76
     midterm
    -0.70
     Princ
    -0.69
    perse
    -0.69
    vironment
    -0.65
     informative
    -0.64
    merce
    -0.64
    phasis
    -0.64
     Flavoring
    -0.64
     Kos
    -0.62
    POSITIVE LOGITS
     cab
    1.05
    rio
    1.03
    aret
    1.00
    leton
    0.81
    oodle
    0.79
    oline
    0.76
     corrid
    0.76
    rera
    0.75
    orter
    0.73
    illo
    0.73
    Act Density 0.005%

    No Known Activations