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

    Neuronpedia

    INDEX
    Explanations

    high-value geographic locations and significant administrative terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wheel
    -0.17
    wheel
    -0.15
    erland
    -0.15
     Hatch
    -0.15
    tah
    -0.15
    AtA
    -0.15
    atchet
    -0.14
    loon
    -0.14
    anvas
    -0.14
    ordova
    -0.14
    POSITIVE LOGITS
    AST
    0.18
     Astroph
    0.17
     Cort
    0.17
     cort
    0.16
    aba
    0.15
    Spe
    0.15
    ç§
    0.15
    oyer
    0.15
    Ast
    0.15
    spe
    0.15
    Act Density 0.030%

    No Known Activations