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

    Neuronpedia

    INDEX
    Explanations

    references to traps and trapping mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дописавши
    -0.75
     henvisninger
    -0.61
    ########.
    -0.60
     either
    -0.55
     escen
    -0.54
     gynhyrchwyd
    -0.52
    颚
    -0.52
     @"/
    -0.51
    cookieParser
    -0.51
     Drinks
    -0.50
    POSITIVE LOGITS
     trap
    1.18
     traps
    1.05
    trap
    1.02
     Traps
    0.97
     Trap
    0.96
    Trap
    0.92
     trapping
    0.90
     trapped
    0.87
     TRAP
    0.73
     dateFormat
    0.68
    Act Density 0.076%

    No Known Activations