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

    Neuronpedia

    INDEX
    Explanations

    phrases comparing or describing similarities with a specific subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference comparisons or analogies, particularly focusing on the word "those."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grac
    -0.64
     pause
    -0.62
     Hes
    -0.59
     Karn
    -0.56
     Count
    -0.55
     Cec
    -0.55
    Second
    -0.54
     Wrestle
    -0.54
    adier
    -0.53
    EMENT
    -0.53
    POSITIVE LOGITS
    usual
    0.80
     describ
    0.80
     usual
    0.75
     prevailing
    0.75
     confir
    0.71
    hots
    0.70
     recip
    0.69
     sket
    0.67
     estab
    0.67
    typ
    0.67
    Act Density 0.084%

    No Known Activations