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

    Neuronpedia

    INDEX
    Explanations

    references to data sources

    oai_token-act-pair · gpt-3.5-turbo

    references to data sources or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tub
    -0.74
    ocol
    -0.72
    needed
    -0.72
    faced
    -0.71
    ãĤ¦ãĤ¹
    -0.70
    ctor
    -0.70
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.69
    hem
    -0.68
     skelet
    -0.68
    purpose
    -0.68
    POSITIVE LOGITS
     afar
    0.96
     whence
    0.82
     inside
    0.79
     abroad
    0.77
     1981
    0.74
     Roll
    0.72
     1979
    0.72
     Washington
    0.71
     1973
    0.70
     1977
    0.69
    Act Density 0.113%

    No Known Activations