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

    Neuronpedia

    INDEX
    Explanations

    phrases related to small and simple structures like shacks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or structures, particularly "shacks"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mpeg
    -0.83
    etheus
    -0.79
    angel
    -0.75
    urnal
    -0.75
    adic
    -0.74
    aed
    -0.70
    KT
    -0.69
    iltr
    -0.68
    kj
    -0.68
     externalToEVAOnly
    -0.68
    POSITIVE LOGITS
    ique
    0.91
    liness
    0.85
     shack
    0.81
    iques
    0.78
    -|
    0.75
    intosh
    0.74
    nesses
    0.72
     cac
    0.72
    lins
    0.70
    cliffe
    0.68
    Act Density 0.024%

    No Known Activations