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

    Neuronpedia

    INDEX
    Explanations

    locations and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to astronomical or geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.76
    anian
    -0.74
    ento
    -0.73
    enegger
    -0.72
    zsche
    -0.64
    english
    -0.64
    anthrop
    -0.62
    terior
    -0.62
     ditch
    -0.62
    rawdownloadcloneembedreportprint
    -0.59
    POSITIVE LOGITS
     Ly
    0.66
     Jade
    0.65
    Rap
    0.64
    ata
    0.64
    Dev
    0.61
     La
    0.57
     Ty
    0.56
     Ab
    0.56
     Sam
    0.55
    Rev
    0.55
    Act Density 0.270%

    No Known Activations