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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the term "iron"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific term related to iron, especially in the context of names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conv
    -0.73
     function
    -0.68
     functions
    -0.67
     restricted
    -0.67
     spend
    -0.66
     priority
    -0.65
     traff
    -0.64
     linger
    -0.64
     suff
    -0.62
     cartel
    -0.62
    POSITIVE LOGITS
    iron
    4.69
    Iron
    1.48
    iro
    1.18
    ira
    1.08
     iron
    1.02
    bol
    0.95
    iring
    0.95
    earth
    0.94
    ivalry
    0.93
    itamin
    0.93
    Act Density 0.007%

    No Known Activations