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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey skepticism or criticism toward concepts and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vedas
    -0.64
     Athenians
    -0.61
     Serap
    -0.58
     Agamemnon
    -0.58
     subsequence
    -0.55
     musket
    -0.54
     itſelf
    -0.53
     Iroquois
    -0.52
     esegu
    -0.52
     Jesuits
    -0.52
    POSITIVE LOGITS
    parsedMessage
    0.91
    
    0.82
    MemoryWarning
    0.82
    SPATH
    0.81
    argout
    0.78
    $}}
    0.74
    complexContent
    0.73
     \%)
    0.71
     }{@
    0.70
    ))->
    0.70
    Act Density 0.190%

    No Known Activations