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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fur
    -0.16
    аÑĢи
    -0.15
    phan
    -0.15
    clin
    -0.14
     stru
    -0.14
    erek
    -0.14
    .invoke
    -0.14
    ầm
    -0.13
    åIJ
    -0.13
     patt
    -0.13
    POSITIVE LOGITS
    ména
    0.16
     âĨij
    0.15
    amaño
    0.15
    746
    0.14
    oring
    0.14
    лоÑĤ
    0.14
    enko
    0.14
    .tk
    0.14
    éĻ¶
    0.13
     human
    0.13
    Act Density 0.044%

    No Known Activations