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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or states of being

    oai_token-act-pair · gpt-3.5-turbo

    instances of Pokémon-related descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lear
    -0.59
     Niet
    -0.56
    Reason
    -0.55
     Apex
    -0.51
    dn
    -0.49
     Ud
    -0.49
     Tinker
    -0.49
     prest
    -0.49
     Incarn
    -0.47
     theirs
    -0.47
    POSITIVE LOGITS
    CLUS
    0.70
    actionDate
    0.65
    chwitz
    0.61
    utenberg
    0.60
    Ĥª
    0.59
    imentary
    0.58
    metics
    0.57
    ileaks
    0.56
    peria
    0.56
    CLAIM
    0.56
    Act Density 0.210%

    No Known Activations