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

    Neuronpedia

    INDEX
    Explanations

    prepositions and determiners in between two specific words

    oai_token-act-pair · gpt-3.5-turbo

    the word "of" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertodd
    -0.76
     redesign
    -0.71
    ogly
    -0.64
     awa
    -0.64
    eele
    -0.62
     reim
    -0.62
     curtain
    -0.61
     disposed
    -0.61
    heses
    -0.60
     tailor
    -0.59
    POSITIVE LOGITS
    THING
    0.95
    course
    0.88
     whatsoever
    0.82
     course
    0.81
     imaginable
    0.75
     sudden
    0.70
     us
    0.66
    Method
    0.65
    these
    0.64
     sorts
    0.64
    Act Density 0.046%

    No Known Activations