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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "So" used to initiate statements or transitions in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RuntimeObject
    -0.38
    Tikang
    -0.34
     relate
    -0.33
    westen
    -0.33
    uce
    -0.32
    坞
    -0.32
     Tal
    -0.32
     Ham
    -0.32
     hau
    -0.32
     Maz
    -0.31
    POSITIVE LOGITS
    :✨
    0.63
    цездатний
    0.62
     GenerationType
    0.58
    dafx
    0.58
     Reverso
    0.56
    sizeCache
    0.56
     disambiguazione
    0.55
     يتيمه
    0.54
    ThroughAttribute
    0.54
     <<<<<<<<<<<<<<
    0.52
    Act Density 0.008%

    No Known Activations