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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential options or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     basically
    -0.19
    èĤ¯å®ļ
    -0.19
     likely
    -0.19
     probably
    -0.19
    åŁºæľ¬
    -0.19
    probably
    -0.17
     almost
    -0.17
    .scalablytyped
    -0.16
     Likely
    -0.16
    Almost
    -0.16
    POSITIVE LOGITS
     depending
    0.34
    depending
    0.28
     some
    0.27
     algún
    0.24
    some
    0.23
     algun
    0.22
     or
    0.22
     qualche
    0.22
     Depending
    0.21
    Depending
    0.21
    Act Density 0.595%

    No Known Activations