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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates or times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.17
    duct
    -0.15
    adelphia
    -0.15
    irk
    -0.15
     Evel
    -0.15
    ACH
    -0.14
    opies
    -0.14
    unca
    -0.14
    ilip
    -0.14
    ovit
    -0.14
    POSITIVE LOGITS
     average
    0.19
    s
    0.18
     contrary
    0.17
    ething
    0.17
    ward
    0.17
    average
    0.17
    contr
    0.16
     rare
    0.16
    ally
    0.15
    surface
    0.15
    Act Density 0.052%

    No Known Activations