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

    Neuronpedia

    INDEX
    Explanations

    crimes or criminal acts being committed

    oai_token-act-pair · gpt-3.5-turbo

    situations involving shocking or controversial events related to children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UNCLASSIFIED
    -0.88
     Organizations
    -0.82
     DOD
    -0.73
    Newsletter
    -0.73
     Commerce
    -0.73
    omever
    -0.73
     Subcommittee
    -0.72
     Manufacturing
    -0.71
    /,
    -0.70
     Assets
    -0.70
    POSITIVE LOGITS
     paed
    1.29
     £
    1.08
     Belfast
    0.96
     homophobic
    0.95
     apologised
    0.94
     maths
    0.94
     apologise
    0.93
     indecent
    0.89
     decap
    0.88
     prank
    0.86
    Act Density 0.677%

    No Known Activations