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

    Neuronpedia

    INDEX
    Explanations

    elements and structures related to educational training programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.17
    Ïĥα
    -0.15
    inos
    -0.15
    icos
    -0.15
    acha
    -0.15
     Scalar
    -0.14
    eru
    -0.14
     Templ
    -0.14
    ello
    -0.14
    oke
    -0.14
    POSITIVE LOGITS
     training
    0.21
    -training
    0.20
    è¨ĵ
    0.18
     train
    0.18
    -trained
    0.18
    training
    0.18
     taught
    0.18
     Training
    0.18
    337
    0.17
    trained
    0.17
    Act Density 0.524%

    No Known Activations