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

    Neuronpedia

    INDEX
    Explanations

    structured mathematical descriptions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deriv
    -0.16
    &m
    -0.15
     çī
    -0.15
     derivatives
    -0.15
     studies
    -0.14
     findings
    -0.14
     results
    -0.14
     fear
    -0.14
     nod
    -0.14
     States
    -0.14
    POSITIVE LOGITS
    toy
    0.19
     procedure
    0.18
     set
    0.17
    prior
    0.17
     family
    0.17
    family
    0.17
     Prior
    0.17
     prior
    0.16
     toy
    0.16
    Ans
    0.16
    Act Density 0.234%

    No Known Activations