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

    Neuronpedia

    INDEX
    Explanations

    references to different types of bottles

    oai_token-act-pair · gpt-3.5-turbo

    references to bottles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.89
    doms
    -0.79
    urities
    -0.72
    yrinth
    -0.71
    ansion
    -0.68
    IFA
    -0.66
    uli
    -0.66
    ominated
    -0.65
    tale
    -0.65
    entity
    -0.65
    POSITIVE LOGITS
     bottles
    1.23
     bottle
    1.18
     Bottle
    1.01
    Bott
    0.93
     Bott
    0.91
     opener
    0.87
     vodka
    0.84
     labelled
    0.84
     refill
    0.83
    mark
    0.81
    Act Density 0.026%

    No Known Activations