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

    Neuronpedia

    INDEX
    Explanations

    terms related to computational systems and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parms
    -0.15
    attles
    -0.14
    732
    -0.14
     scal
    -0.14
    heel
    -0.14
    _caps
    -0.14
    ahan
    -0.14
    .sky
    -0.14
     yaw
    -0.14
    Scaling
    -0.13
    POSITIVE LOGITS
     word
    0.23
     pumping
    0.22
     words
    0.21
    dfa
    0.20
    prefix
    0.20
     alphabet
    0.20
    -word
    0.20
     Kle
    0.20
    recogn
    0.20
     autom
    0.19
    Act Density 0.022%

    No Known Activations