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

    Neuronpedia

    INDEX
    Explanations

    references to interviews

    oai_token-act-pair · gpt-3.5-turbo

    references to interviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    math
    -0.74
    mil
    -0.73
     rejoice
    -0.68
    blue
    -0.66
    borgh
    -0.65
    DIV
    -0.62
    bn
    -0.61
    axy
    -0.59
    wikipedia
    -0.58
     Flavoring
    -0.58
    POSITIVE LOGITS
    ees
    1.33
    ee
    1.15
     conducted
    1.04
     interview
    0.89
     transcripts
    0.88
     subjects
    0.87
    ioned
    0.84
     interviews
    0.84
     Transcript
    0.81
     transcript
    0.80
    Act Density 0.059%

    No Known Activations