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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "net" and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.00
    rungsseite
    -0.56
    Törté
    -0.55
     hyvä
    -0.53
    /*!
    -0.52
    house
    -0.50
    /***
    -0.49
     tarko
    -0.49
    glPushMatrix
    -0.49
    engkapi
    -0.48
    POSITIVE LOGITS
     sappi
    1.16
     perfet
    1.10
     accla
    1.07
     Realt
    1.06
     philanth
    1.02
     Strukt
    1.01
     bett
    1.00
     haup
    0.99
     maneu
    0.99
     exorbit
    0.99
    Act Density 0.573%

    No Known Activations