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

    Neuronpedia

    INDEX
    Explanations

    person names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.84
    âĶĢâĶĢ
    -0.70
    etheless
    -0.65
    duino
    -0.64
     HMS
    -0.62
     Lanka
    -0.62
     FANTASY
    -0.60
     Imran
    -0.59
     Emblem
    -0.58
    ãĥŁ
    -0.57
    POSITIVE LOGITS
    zinski
    0.78
    zen
    0.78
    heny
    0.76
    lett
    0.73
    inski
    0.73
    zik
    0.73
    linger
    0.72
    bey
    0.72
    beck
    0.71
    zman
    0.71
    Act Density 0.254%

    No Known Activations