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

    Neuronpedia

    INDEX
    Explanations

    verbs related to perception or observation

    oai_token-act-pair · gpt-3.5-turbo

    words and expressions associated with various forms of "seeping" or "creeping."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holding
    -0.83
    par
    -0.79
    phot
    -0.76
    anchester
    -0.76
    sw
    -0.73
    izes
    -0.72
    beit
    -0.72
    folios
    -0.71
    ably
    -0.70
    hips
    -0.70
    POSITIVE LOGITS
    eper
    0.80
    arthed
    0.73
     Elephant
    0.72
    otten
    0.71
    emon
    0.69
     eaves
    0.68
     Horses
    0.67
     Cyber
    0.67
     Doctrine
    0.65
     Wonders
    0.63
    Act Density 0.017%

    No Known Activations