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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a direction, such as "to" or "in", often indicating a relationship between entities

    oai_token-act-pair · gpt-3.5-turbo

    dominant prepositions and additional context words in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoe
    -0.67
    orks
    -0.64
    º
    -0.61
    fter
    -0.61
     Lines
    -0.60
    âĸij
    -0.59
    ealous
    -0.59
     forgot
    -0.59
    vier
    -0.59
    ato
    -0.59
    POSITIVE LOGITS
    arching
    0.71
     WW
    0.70
     regard
    0.66
     redeem
    0.63
    isSpecialOrderable
    0.60
     Concord
    0.60
     augment
    0.60
     govern
    0.59
     appeal
    0.58
     Qt
    0.58
    Act Density 0.221%

    No Known Activations