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

    Neuronpedia

    INDEX
    Explanations

    instances of blog posts mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to blog posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tsky
    -0.75
    osph
    -0.72
    esthetic
    -0.70
    iaz
    -0.69
    estial
    -0.68
    aucas
    -0.68
    ãĤ¤ãĥĪ
    -0.68
    ibles
    -0.66
    achev
    -0.66
    othal
    -0.66
    POSITIVE LOGITS
     announcing
    0.92
     detailing
    0.80
    mortem
    0.77
    lished
    0.75
    gres
    0.74
     outlining
    0.73
     lamb
    0.72
     issued
    0.71
     touting
    0.69
     penned
    0.67
    Act Density 0.031%

    No Known Activations