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

    Neuronpedia

    INDEX
    Explanations

    references to criminal activity and notorious criminals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    меÑĩ
    -0.16
    iage
    -0.15
    orque
    -0.14
    vpn
    -0.14
     Kont
    -0.14
    leep
    -0.14
    obel
    -0.13
    ãĤĥ
    -0.13
    onga
    -0.13
    amina
    -0.13
    POSITIVE LOGITS
    abilia
    0.17
    ril
    0.15
    tracker
    0.14
     morale
    0.14
    auer
    0.14
     spree
    0.14
    ToObject
    0.14
    ulings
    0.13
     Persona
    0.13
     operating
    0.13
    Act Density 0.022%

    No Known Activations