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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, names, and political events in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lisi
    -0.84
     Landis
    -0.81
     africain
    -0.78
    Loch
    -0.78
     Catania
    -0.76
     tapa
    -0.75
    chenkt
    -0.75
     Unger
    -0.74
    olig
    -0.74
    cenza
    -0.73
    POSITIVE LOGITS
     Jaco
    0.91
    Pom
    0.83
     NEO
    0.82
     COA
    0.82
     Jasmin
    0.79
     Tyl
    0.78
     Esau
    0.76
     Cassel
    0.75
     Pom
    0.75
    FormState
    0.75
    Act Density 2.166%

    No Known Activations