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

    Neuronpedia

    INDEX
    Explanations

    financial terms or items, especially related to sales and products

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "all" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.64
     fewer
    -0.59
     precisely
    -0.58
    SHIP
    -0.57
    ly
    -0.56
     disclaimer
    -0.55
     Triple
    -0.54
    ··
    -0.54
     trusting
    -0.53
     centrif
    -0.53
    POSITIVE LOGITS
    enged
    1.36
    iance
    1.35
    adium
    1.31
    enge
    1.29
    ength
    1.26
    axy
    1.17
    ibrary
    1.12
    ergic
    1.11
    enges
    1.11
    iances
    1.08
    Act Density 0.034%

    No Known Activations