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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andler
    -0.17
    963
    -0.15
     Ortiz
    -0.14
    çĪµ
    -0.14
     Bros
    -0.14
    ower
    -0.14
    AYS
    -0.14
    eyer
    -0.14
    ég
    -0.13
    duck
    -0.13
    POSITIVE LOGITS
    990
    0.17
    cdb
    0.16
    ifer
    0.15
    inct
    0.15
     lif
    0.15
     Invent
    0.15
     hoop
    0.15
    oplast
    0.14
    ylland
    0.14
     cur
    0.14
    Act Density 0.148%

    No Known Activations