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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a comparison or relative positioning

    oai_token-act-pair · gpt-3.5-turbo

    the term "relatively" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Polo
    -0.83
    ieu
    -0.80
    inis
    -0.74
    tein
    -0.73
    arta
    -0.71
    halla
    -0.70
     Landing
    -0.70
    iens
    -0.70
    andel
    -0.70
    rings
    -0.68
    POSITIVE LOGITS
     tame
    0.98
     unpop
    0.96
     unaffected
    0.94
     unchanged
    0.91
     insignificant
    0.90
     innocuous
    0.89
     scarce
    0.89
     insensitive
    0.87
     benign
    0.87
     inexpensive
    0.86
    Act Density 0.014%

    No Known Activations