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

    Neuronpedia

    INDEX
    Explanations

    the word "those" followed by numerical values

    oai_token-act-pair · gpt-3.5-turbo

    the word "those" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ess
    -0.59
    inez
    -0.59
    ework
    -0.59
    ist
    -0.58
    encer
    -0.58
    lim
    -0.56
    ftime
    -0.56
    lyn
    -0.56
     Ltd
    -0.56
    ista
    -0.55
    POSITIVE LOGITS
     those
    2.74
    those
    2.46
     Those
    1.83
    Those
    1.80
     these
    1.47
    these
    1.30
     ones
    1.24
     others
    1.09
     THESE
    1.08
     them
    1.05
    Act Density 0.059%

    No Known Activations