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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic literature and research

    oai_token-act-pair · gpt-3.5-turbo

    details about academic authors and their publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.69
     condos
    -0.65
     respawn
    -0.64
     stret
    -0.61
     perimeter
    -0.58
     draining
    -0.58
     turf
    -0.58
     chopping
    -0.58
     sealing
    -0.57
     congest
    -0.56
    POSITIVE LOGITS
     summar
    0.82
     summarizes
    0.76
     essays
    0.75
    ibliography
    0.74
    ournals
    0.73
    published
    0.71
     essay
    0.70
     summarized
    0.67
    Science
    0.66
     excerpts
    0.66
    Act Density 1.916%

    No Known Activations