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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships or actions involving subjects and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Newsletter
    -0.65
    itiz
    -0.64
    adian
    -0.63
    Hot
    -0.62
    âĿ
    -0.62
    adia
    -0.60
    ret
    -0.59
    Residents
    -0.59
    Definition
    -0.59
    Ľ
    -0.58
    POSITIVE LOGITS
     whom
    0.80
     which
    0.74
     unsus
    0.71
    ardless
    0.70
    which
    0.68
     perhaps
    0.67
    nown
    0.66
     simultane
    0.65
     evidenced
    0.64
     whence
    0.63
    Act Density 0.390%

    No Known Activations