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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to comparisons or relationships

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and conjunctions that indicate relationships and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rake
    -0.70
     breeze
    -0.64
     supers
    -0.59
     weeds
    -0.58
     Whit
    -0.58
     messed
    -0.57
     glare
    -0.56
     baths
    -0.56
     weed
    -0.55
     REPL
    -0.55
    POSITIVE LOGITS
    vised
    0.77
    adr
    0.77
    atever
    0.77
    appropriately
    0.76
    ucket
    0.75
    asy
    0.74
    alde
    0.73
    rov
    0.73
    İĭ
    0.73
    ¿½
    0.72
    Act Density 0.742%

    No Known Activations