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

    Neuronpedia

    INDEX
    Explanations

    words related to product introductions or productions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "introducing" and variations of "produced" or "producer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grail
    -0.67
     Romanian
    -0.67
     Siberian
    -0.66
     Danish
    -0.66
     Bulgarian
    -0.66
    avorite
    -0.65
     Frankfurt
    -0.65
     sleeper
    -0.64
     Greeks
    -0.63
     Greek
    -0.63
    POSITIVE LOGITS
    ctions
    1.38
    ctory
    1.32
    cer
    1.31
    cing
    1.28
    ctive
    1.18
    cers
    1.16
    ce
    1.14
    cible
    1.14
    cial
    1.13
    pta
    1.08
    Act Density 0.021%

    No Known Activations