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

    Neuronpedia

    INDEX
    Explanations

    terms associated with legality and illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mijne
    -0.92
     zijne
    -0.91
     avoient
    -0.89
     idéia
    -0.86
     Bewußt
    -0.85
    ambién
    -0.82
     étoient
    -0.80
     Italij
    -0.80
     enfans
    -0.78
     miniaturka
    -0.78
    POSITIVE LOGITS
     illegal
    0.77
     legal
    0.67
     index
    0.60
    index
    0.59
     Legal
    0.56
     Il
    0.56
     
    0.54
    ↵↵
    0.54
     Index
    0.54
    uuid
    0.52
    Act Density 0.447%

    No Known Activations