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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "guests."

    oai_token-act-pair · gpt-3.5-turbo

    references to attendees or participants in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.73
     Ecology
    -0.66
    ²¾
    -0.63
     oxide
    -0.61
    rates
    -0.60
     Shotgun
    -0.59
    ãĥ£
    -0.59
    states
    -0.59
     tracts
    -0.57
    ãĤ¿
    -0.57
    POSITIVE LOGITS
    hip
    1.05
     guests
    0.92
     Guests
    0.92
    erv
    0.89
    hips
    0.87
    afety
    0.77
    peed
    0.77
    ele
    0.76
     disembark
    0.74
    pread
    0.73
    Act Density 0.028%

    No Known Activations