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

    Neuronpedia

    INDEX
    Explanations

    words related to support or assistance

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to support and encouragement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovie
    -0.79
    otine
    -0.65
    affe
    -0.61
     Spartan
    -0.60
     Tale
    -0.58
     Ri
    -0.58
     dataset
    -0.58
     Avenger
    -0.58
     Reich
    -0.58
     Mash
    -0.58
    POSITIVE LOGITS
    fully
    0.89
    ably
    0.82
    ifully
    0.82
     everywhere
    0.81
    lessly
    0.81
    ously
    0.79
    ALLY
    0.77
    DragonMagazine
    0.77
    iless
    0.77
    cards
    0.77
    Act Density 0.415%

    No Known Activations