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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic application requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Attribution
    -0.15
    .hu
    -0.15
    uctions
    -0.15
    nett
    -0.14
     nett
    -0.14
    laden
    -0.14
    Weekly
    -0.14
     Peg
    -0.14
    aret
    -0.14
    inci
    -0.14
    POSITIVE LOGITS
     transcripts
    0.33
     transcript
    0.33
     dipl
    0.32
     Transcript
    0.31
     diploma
    0.31
     Dipl
    0.31
     degree
    0.30
     degrees
    0.27
     Diploma
    0.27
     Degree
    0.26
    Act Density 0.019%

    No Known Activations