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

    Neuronpedia

    INDEX
    Explanations

    phrases related to travel and transportation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships between people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aborted
    -0.75
     flares
    -0.65
     bundled
    -0.65
     hijacked
    -0.61
     fading
    -0.60
     laure
    -0.59
     Arrows
    -0.59
     Rex
    -0.58
     Rohingya
    -0.58
     clustered
    -0.58
    POSITIVE LOGITS
    morrow
    1.03
    prison
    1.02
    date
    1.01
    dos
    1.01
    advertising
    1.00
    inf
    0.98
    acqu
    0.97
    sent
    0.97
    order
    0.95
    distance
    0.93
    Act Density 0.033%

    No Known Activations