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

    Neuronpedia

    INDEX
    Explanations

    words related to introducing or discussing various topics or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "introducing" and related variations frequently in the context of introducing topics or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sleeper
    -0.70
     Frankfurt
    -0.68
     Mara
    -0.67
     Immunity
    -0.67
     Beir
    -0.63
     Bulgarian
    -0.62
    illary
    -0.62
    avorite
    -0.61
     Carth
    -0.61
     Siberian
    -0.61
    POSITIVE LOGITS
    ctory
    1.56
    ctions
    1.35
    cing
    1.24
    pta
    1.11
    cible
    1.06
    cer
    1.06
    ce
    1.05
    ction
    1.00
    ations
    1.00
    cci
    0.98
    Act Density 0.032%

    No Known Activations