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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetitive or ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    side
    -0.16
    à¹Ģลà¸Ĥ
    -0.15
     Bew
    -0.13
    util
    -0.13
    nest
    -0.13
    ums
    -0.13
    μο
    -0.13
     hy
    -0.13
    #End
    -0.13
    alleries
    -0.13
    POSITIVE LOGITS
     against
    0.26
    against
    0.26
     Against
    0.24
    Against
    0.22
     hand
    0.21
    contre
    0.19
     counter
    0.18
    iani
    0.18
     beyond
    0.17
    inion
    0.17
    Act Density 0.024%

    No Known Activations