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

    Neuronpedia

    INDEX
    Explanations

    phrases related to institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that mention notable institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pit
    -0.76
     extinct
    -0.74
     elusive
    -0.73
     prey
    -0.71
     dips
    -0.71
     phantom
    -0.70
     fade
    -0.70
     slightest
    -0.70
     throb
    -0.69
     stamped
    -0.69
    POSITIVE LOGITS
     Along
    1.09
     Together
    1.05
     Additionally
    1.04
     Their
    1.00
     Among
    0.98
     Previously
    0.97
     His
    0.96
     Similarly
    0.93
     They
    0.91
     He
    0.90
    Act Density 0.824%

    No Known Activations