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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of famous artists and public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Newsletter
    -0.74
    RIC
    -0.62
     CPR
    -0.60
     salsa
    -0.59
     Duterte
    -0.58
    BLIC
    -0.56
     contingent
    -0.56
    CENT
    -0.55
     recoil
    -0.55
     Zac
    -0.55
    POSITIVE LOGITS
    uren
    0.96
    enburg
    0.86
    eden
    0.84
    burgh
    0.81
    ulkan
    0.78
    eren
    0.75
    atu
    0.74
    chn
    0.73
    ouver
    0.72
    wen
    0.71
    Act Density 0.056%

    No Known Activations