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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns related to collective human experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to "us" and "them" dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egu
    -0.63
    hai
    -0.62
     Waiting
    -0.59
     ASA
    -0.58
    itton
    -0.58
    )].
    -0.57
     sometime
    -0.57
    ructose
    -0.57
     assembly
    -0.56
     BB
    -0.55
    POSITIVE LOGITS
     nor
    1.42
     whatsoever
    1.36
    nor
    1.01
     anymore
    0.99
     dime
    0.92
     necessarily
    0.89
     EVER
    0.85
     lasts
    0.84
     except
    0.83
    soever
    0.83
    Act Density 0.151%

    No Known Activations