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

    Neuronpedia

    INDEX
    Explanations

    verbs and indications of roles or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erved
    -0.15
    activex
    -0.14
    BlockSize
    -0.14
    ì§
    -0.14
    arak
    -0.14
    apter
    -0.14
    Ĺi
    -0.14
    ticker
    -0.13
    iger
    -0.13
    ãĥªãĤ¹
    -0.13
    POSITIVE LOGITS
     paid
    0.39
     Paid
    0.34
    paid
    0.33
     hired
    0.33
    Paid
    0.32
    -paid
    0.30
     asked
    0.30
     tasked
    0.27
     responsible
    0.27
     unpaid
    0.26
    Act Density 0.196%

    No Known Activations