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

    Neuronpedia

    INDEX
    Explanations

    references to horror elements that create a creepy or unsettling atmosphere

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trái
    -0.37
    impresa
    -0.36
    essentiel
    -0.36
    organizzazione
    -0.35
    feather
    -0.35
     ringan
    -0.35
     namanya
    -0.35
     väli
    -0.35
     mariposas
    -0.34
     niezbęd
    -0.34
    POSITIVE LOGITS
     haunted
    0.58
     eerie
    0.57
     haunt
    0.54
    setupUi
    0.54
    RegressionTest
    0.54
     spooky
    0.54
     ghost
    0.53
    anoke
    0.53
     horror
    0.52
     undead
    0.52
    Act Density 0.230%

    No Known Activations