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

    Neuronpedia

    INDEX
    Explanations

    words related to imitation or replication

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and concepts related to mimicry and possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gamer
    -0.67
    bug
    -0.64
     Valley
    -0.63
    spin
    -0.63
     Typhoon
    -0.63
     Vigil
    -0.62
     Command
    -0.61
    FINE
    -0.61
    beard
    -0.60
     Hunger
    -0.59
    POSITIVE LOGITS
    okin
    0.94
    illus
    0.94
    ortun
    0.92
    eki
    0.89
    ez
    0.86
    arro
    0.86
    chwitz
    0.85
    ortment
    0.84
    imum
    0.83
    inet
    0.82
    Act Density 0.022%

    No Known Activations