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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.85
     Releases
    -0.69
     Highlights
    -0.68
     Response
    -0.66
     Sins
    -0.62
    inav
    -0.61
     Neb
    -0.61
     Shall
    -0.61
     Offer
    -0.61
     Letters
    -0.60
    POSITIVE LOGITS
    nt
    0.90
     substituted
    0.81
     deemed
    0.80
    çĶ°
    0.79
     replaced
    0.79
     indistinguishable
    0.77
     inevitably
    0.76
     supposed
    0.76
     absent
    0.75
     predominant
    0.75
    Act Density 0.370%

    No Known Activations