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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arkan
    -0.16
     kia
    -0.15
     Webster
    -0.15
    æļ®
    -0.14
    دÙĩاÛĮ
    -0.14
    GridColumn
    -0.13
    peat
    -0.13
     Sisters
    -0.13
     Mob
    -0.13
    akers
    -0.13
    POSITIVE LOGITS
    idla
    0.17
     older
    0.15
    anka
    0.15
    older
    0.14
    HL
    0.14
    éĢ
    0.14
    incinn
    0.14
    ulace
    0.14
    _subplot
    0.14
    ughs
    0.14
    Act Density 0.014%

    No Known Activations