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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning an action or event happening at a specific location

    oai_token-act-pair · gpt-3.5-turbo

    articles indicating presence or general references in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĿ
    -0.78
     favourites
    -0.74
    marks
    -0.73
    stars
    -0.73
    ontent
    -0.73
    fn
    -0.72
    holders
    -0.72
     favorites
    -0.72
    /-
    -0.72
    plates
    -0.71
    POSITIVE LOGITS
     nutshell
    1.06
     vein
    0.98
     manner
    0.95
     labyrinth
    0.90
     guise
    0.90
     dense
    0.90
     courtroom
    0.89
     vain
    0.89
     midst
    0.88
     wake
    0.88
    Act Density 0.293%

    No Known Activations