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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or criminal activity

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of convoys or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BALL
    -0.78
    WARE
    -0.71
    WAYS
    -0.71
     Pathfinder
    -0.67
    blind
    -0.66
    ¥µ
    -0.66
     barrier
    -0.64
    wagen
    -0.62
    white
    -0.62
    THER
    -0.61
    POSITIVE LOGITS
    icts
    1.12
    ique
    1.09
    iques
    1.08
    ise
    1.05
    olution
    0.94
    ulsive
    0.93
    ulsion
    0.92
    irus
    0.92
     conv
    0.91
    olver
    0.90
    Act Density 0.017%

    No Known Activations