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

    Neuronpedia

    INDEX
    Explanations

    instances of arrests and related legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acre
    -0.17
    urpose
    -0.15
    irm
    -0.15
    anch
    -0.15
    ittle
    -0.15
    ikat
    -0.14
    artz
    -0.14
    gth
    -0.14
    oller
    -0.13
    rint
    -0.13
    POSITIVE LOGITS
    ees
    0.25
     warrant
    0.23
     WARRANT
    0.20
    ee
    0.20
    گاÙĩ
    0.20
     warrants
    0.19
    ingly
    0.18
    ivals
    0.17
    eeee
    0.17
    aurant
    0.17
    Act Density 0.017%

    No Known Activations