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

    Neuronpedia

    INDEX
    Explanations

    culinary instructions or cooking techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebo
    -0.17
    inand
    -0.15
     takım
    -0.14
    eut
    -0.14
     cigaret
    -0.14
     okol
    -0.14
    oje
    -0.14
     mashed
    -0.13
    bis
    -0.13
    ardon
    -0.13
    POSITIVE LOGITS
     substitute
    0.26
     substitutions
    0.26
     substitution
    0.26
     Substitute
    0.25
     substitutes
    0.23
     substituted
    0.23
     substit
    0.22
     SUBSTITUTE
    0.21
     omitted
    0.20
     instead
    0.20
    Act Density 0.058%

    No Known Activations