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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "each" or "a" indicating enumeration or unspecified quantity

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ulele
    -0.81
     архивлан
    -0.73
    AndEndTag
    -0.73
    脚注の使い方
    -0.72
    Personensuche
    -0.71
     Mosca
    -0.71
    Бахар
    -0.71
     auroit
    -0.71
     SwitchCompat
    -0.70
     feroit
    -0.70
    POSITIVE LOGITS
    inigungs
    0.48
    
    0.48
     Mrs
    0.47
    findpost
    0.46
     McGu
    0.46
     H
    0.45
    nhold
    0.45
     aren
    0.45
     "
    0.44
     оформ
    0.43
    Act Density 0.014%

    No Known Activations