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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of entities followed by possessive markers (such as "'s")

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "s" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rounds
    -0.71
     Pharaoh
    -0.70
     Slate
    -0.69
     Slug
    -0.66
     Reef
    -0.64
     Seas
    -0.64
    Film
    -0.63
     Salon
    -0.61
     Ago
    -0.61
    PN
    -0.61
    POSITIVE LOGITS
    selves
    1.14
    ELF
    1.05
     own
    0.96
    ources
    0.94
    outhern
    0.88
    ustainable
    0.87
    atically
    0.85
    oes
    0.83
    essions
    0.82
    leeve
    0.81
    Act Density 0.155%

    No Known Activations