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

    Neuronpedia

    INDEX
    Explanations

    references to caves

    oai_token-act-pair · gpt-3.5-turbo

    references to caves and cave-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andum
    -0.68
    ial
    -0.59
    LM
    -0.59
    isconsin
    -0.59
    ifa
    -0.59
    oppable
    -0.58
    abeth
    -0.58
    IFA
    -0.58
    iating
    -0.58
     FTA
    -0.57
    POSITIVE LOGITS
     Dwell
    1.31
    yrinth
    1.19
     dwell
    1.09
    door
    1.01
     dwelling
    0.99
     cave
    0.99
    lain
    0.95
    resses
    0.94
     crawl
    0.93
     dwellings
    0.91
    Act Density 0.105%

    No Known Activations