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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kuuta
    -0.64
     argint
    -0.58
    droje
    -0.55
    TintMode
    -0.54
    saraba
    -0.53
    DialogTitle
    -0.53
    theless
    -0.51
     CiNii
    -0.51
    Tikang
    -0.50
    margins
    -0.50
    POSITIVE LOGITS
     comprised
    1.40
     consists
    1.35
     consisted
    1.29
     comprising
    1.27
     comprises
    1.25
     consisting
    1.25
     consist
    1.25
     gồm
    1.19
     terdiri
    1.16
     comprise
    1.12
    Act Density 0.287%

    No Known Activations