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

    Neuronpedia

    INDEX
    Explanations

    phrases related to writing blog posts.

    oai_token-act-pair · gpt-3.5-turbo

    mentions of blog posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osph
    -0.80
    cgi
    -0.74
    omaly
    -0.72
    ranch
    -0.72
    tsky
    -0.72
    aucas
    -0.68
     isot
    -0.66
    bowl
    -0.66
    ubi
    -0.65
    species
    -0.65
    POSITIVE LOGITS
     announcing
    1.05
     detailing
    0.87
     entitled
    0.81
     outlining
    0.80
     touting
    0.78
     titled
    0.77
     accompanying
    0.77
     describing
    0.74
    lished
    0.73
     ---------
    0.73
    Act Density 0.072%

    No Known Activations