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

    Neuronpedia

    INDEX
    Explanations

    specific locations and geographic references within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neté
    -0.73
     sanitaires
    -0.62
     Blackpool
    -0.60
     Preferencias
    -0.59
    swal
    -0.54
    Fuckin
    -0.54
    ScopeManager
    -0.54
     فريبيس
    -0.53
     ब्रेकडाउन
    -0.52
     tattoos
    -0.52
    POSITIVE LOGITS
     tennis
    0.61
    tennis
    0.60
     Upper
    0.55
    Espèce
    0.55
    etCode
    0.54
     Tennis
    0.54
    +#+#
    0.53
     luxury
    0.53
     Sloane
    0.53
    wealth
    0.53
    Act Density 0.196%

    No Known Activations