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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rule-breaking and illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \grid
    -0.19
    ãĥ¼ãĥł
    -0.17
    orges
    -0.15
    avier
    -0.15
    udo
    -0.14
    .reporting
    -0.14
    agher
    -0.14
    ULO
    -0.14
    parsers
    -0.14
    Äĥn
    -0.14
    POSITIVE LOGITS
     s
    0.18
     unauthorized
    0.16
     bo
    0.15
    391
    0.15
     le
    0.14
     Rubin
    0.14
     Pitch
    0.14
     without
    0.14
     cons
    0.14
     People
    0.14
    Act Density 0.143%

    No Known Activations