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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names containing the sequence "aus"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Haus" and its variations, likely indicating a focus on specific places or contexts related to housing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢ
    -0.70
     td
    -0.65
     cane
    -0.61
    Assembly
    -0.61
     cue
    -0.59
    OUT
    -0.59
     rim
    -0.59
    BOOK
    -0.58
    dfx
    -0.58
     short
    -0.58
    POSITIVE LOGITS
    chwitz
    1.12
    aus
    1.00
    kas
    0.94
    ylum
    0.90
    hip
    0.84
    adian
    0.84
    ername
    0.83
    heon
    0.82
    ensical
    0.82
    hent
    0.81
    Act Density 0.012%

    No Known Activations