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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographic locations or landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.92
     Barbier
    -0.89
     שוליים
    -0.74
     myſelf
    -0.74
     Blon
    -0.73
     Muriel
    -0.72
     gynhyrchwyd
    -0.71
     Monfieur
    -0.70
     begre
    -0.70
     themſelves
    -0.69
    POSITIVE LOGITS
     Kings
    0.81
    sap
    0.79
     Hin
    0.75
    sag
    0.73
    uskas
    0.73
    gatsby
    0.73
    Hin
    0.72
    γέν
    0.72
    she
    0.71
     Alvarado
    0.71
    Act Density 0.005%

    No Known Activations