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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses that indicate possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.26
     doubtnut
    -1.13
     -"
    -1.10
     poffible
    -1.09
     '"
    -1.09
     Jefus
    -1.08
     pleaf
    -1.08
    。"
    -1.07
     Majefty
    -1.07
     Chrift
    -1.06
    POSITIVE LOGITS
     “
    1.86
    ’
    1.82
    ”
    1.73
     ‘
    1.69
    ’,
    1.67
    ’.
    1.60
    .’
    1.56
    “
    1.56
    ,’
    1.50
    ”,
    1.48
    Act Density 0.718%

    No Known Activations