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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic research and funding initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orian
    -0.17
    indow
    -0.16
     research
    -0.16
     perch
    -0.16
    ë¡ł
    -0.16
    vak
    -0.15
    PLAY
    -0.15
    /operators
    -0.14
     theory
    -0.14
    iale
    -0.14
    POSITIVE LOGITS
    er
    0.22
    Gate
    0.21
    gate
    0.18
    erse
    0.17
    zym
    0.17
    rego
    0.17
    urdy
    0.16
    |array
    0.16
    -active
    0.16
     Triangle
    0.15
    Act Density 0.028%

    No Known Activations