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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating direction or position

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and relational phrases indicating connections or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    break
    -0.64
    craft
    -0.64
    cake
    -0.62
    glass
    -0.59
    alogue
    -0.59
    igr
    -0.58
    ãĥ³ãĤ¸
    -0.58
    Pg
    -0.57
    horn
    -0.56
    art
    -0.55
    POSITIVE LOGITS
     whom
    1.13
     which
    1.02
    which
    0.82
     whence
    0.80
     determining
    0.75
     respectively
    0.75
     ensuring
    0.71
     minimizing
    0.69
     recommending
    0.67
     allowing
    0.67
    Act Density 0.627%

    No Known Activations