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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations or administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heuer
    -0.42
     Vail
    -0.41
    tagHelperRunner
    -0.39
     Metzger
    -0.37
     Munich
    -0.36
     Austrian
    -0.35
     Schweizer
    -0.35
     Swiss
    -0.34
     pozw
    -0.34
     Bavarian
    -0.34
    POSITIVE LOGITS
     linkovi
    0.66
     Infórmanos
    0.66
    Berlin
    0.61
     GDR
    0.61
     Spree
    0.60
    InitVars
    0.59
     DDR
    0.57
     Berlin
    0.57
     Bioaccumulative
    0.56
     berlin
    0.55
    Act Density 0.471%

    No Known Activations