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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contacting authorities, support, or relevant personnel for assistance or guidance

    oai_token-act-pair · gpt-3.5-turbo

    references to communication and reporting to authorities or support services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athered
    -0.64
    eat
    -0.63
     bets
    -0.61
    ardless
    -0.61
    itialized
    -0.61
    phy
    -0.58
    skirts
    -0.57
     Beats
    -0.56
     dominates
    -0.56
     combustion
    -0.56
    POSITIVE LOGITS
     informing
    1.08
     requesting
    1.08
     hotline
    1.08
     about
    1.05
    mbuds
    1.03
     regarding
    1.00
     ABOUT
    0.96
     asking
    0.95
     directly
    0.93
     inquire
    0.92
    Act Density 0.398%

    No Known Activations