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

    Neuronpedia

    INDEX
    Explanations

    references to the moon and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashvili
    -0.70
    basicConfig
    -0.64
     zm
    -0.64
    πισ
    -0.63
    itans
    -0.62
    fhir
    -0.61
    ReusableCell
    -0.61
    ANNES
    -0.60
    terdam
    -0.58
    rildi
    -0.58
    POSITIVE LOGITS
    ue
    0.92
     Moon
    0.83
    Menu
    0.80
    UE
    0.74
     MOON
    0.73
    Moon
    0.72
     moon
    0.71
     moonlight
    0.70
     Menu
    0.67
     keyword
    0.66
    Act Density 0.038%

    No Known Activations