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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and mountain ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SpringRunner
    -0.47
     OFDb
    -0.41
    Rhestr
    -0.40
    APORE
    -0.39
     AssemblyCompany
    -0.39
    AddTagHelper
    -0.39
    UrlResolution
    -0.39
    ArgsConstructor
    -0.38
    ScopeManager
    -0.37
    istoitu
    -0.37
    POSITIVE LOGITS
     mountain
    2.53
     mountains
    2.45
    mountain
    2.16
     Mountains
    2.11
    mountains
    2.05
     Mountain
    2.02
    Mountain
    1.97
     mountainous
    1.95
    Mountains
    1.94
     MOUNTAIN
    1.90
    Act Density 0.400%

    No Known Activations