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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "Iron" followed by a single capitalized word

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Iron" related to various contexts, particularly in media and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uated
    -0.82
    enance
    -0.77
    arre
    -0.77
    upid
    -0.72
    ĸļ
    -0.67
    absolute
    -0.67
    76561
    -0.67
    lished
    -0.67
    perture
    -0.66
    uates
    -0.65
    POSITIVE LOGITS
    clad
    1.20
    works
    0.90
     Age
    0.87
    heart
    0.85
     Maiden
    0.84
    Python
    0.83
    wood
    0.80
     ore
    0.80
    forge
    0.80
    claw
    0.78
    Act Density 0.013%

    No Known Activations