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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, particularly those associated with "San" in their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebVitals
    -1.05
     betweenstory
    -1.04
     Roskov
    -0.96
    InjectAttribute
    -0.92
     препратки
    -0.89
     Guiana
    -0.85
    IContainer
    -0.85
    EDEFAULT
    -0.85
     vVar
    -0.84
    ]){
    -0.84
    POSITIVE LOGITS
     San
    1.41
    San
    1.28
     SAN
    1.22
     Sandi
    1.16
     Sanford
    1.10
    SAN
    1.10
     san
    1.10
    san
    1.01
     sanctions
    0.97
     Sanctions
    0.97
    Act Density 0.199%

    No Known Activations