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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to proximity and connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arda
    -0.16
    asma
    -0.15
    书记
    -0.15
    ORIZ
    -0.15
     Bilim
    -0.14
    iez
    -0.14
    /TT
    -0.14
    olithic
    -0.14
    romise
    -0.14
    unnel
    -0.14
    POSITIVE LOGITS
    ataire
    0.17
    ville
    0.16
    گرد
    0.15
    sett
    0.14
    .struct
    0.14
    VILLE
    0.14
    aison
    0.13
     words
    0.13
     full
    0.13
     specialized
    0.13
    Act Density 0.038%

    No Known Activations