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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.31
     propOrder
    -1.19
    transQ
    -1.12
    +#+#
    -1.07
    fromnode
    -1.04
     '\\;'
    -1.04
    principalColumn
    -1.03
    oredCriteria
    -1.02
     Roskov
    -1.02
     disambiguazione
    -0.99
    POSITIVE LOGITS
    \
    0.60
     is
    0.54
    .
    0.54
     
    0.54
     are
    0.53
     .
    0.52
    :
    0.51
    -
    0.50
    ...
    0.47
     can
    0.47
    Act Density 0.485%

    No Known Activations