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

    Neuronpedia

    INDEX
    Explanations

    specific actions or events related to multiple varied topics

    oai_token-act-pair · gpt-3.5-turbo

    nouns and phrases related to governance and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Subject
    -0.53
    rules
    -0.52
    Course
    -0.51
    Reviewed
    -0.51
     Celt
    -0.51
     Gaw
    -0.50
    Fight
    -0.50
    Cand
    -0.50
    romeda
    -0.50
    ones
    -0.49
    POSITIVE LOGITS
     woes
    0.61
    hett
    0.53
     territories
    0.53
     cousins
    0.51
     selves
    0.51
     condo
    0.49
    ãĥķãĤ©
    0.49
     holdings
    0.49
     thumbs
    0.49
     rampage
    0.48
    Act Density 0.483%

    No Known Activations