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

    Neuronpedia

    INDEX
    Explanations

    words related to continuation or progression in a series or sequence

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases emphasizing continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cree
    -0.65
     Neigh
    -0.62
     Kids
    -0.62
     Dre
    -0.60
     Burg
    -0.59
    ropolitan
    -0.59
    WN
    -0.58
     Milan
    -0.58
    gie
    -0.58
     Federal
    -0.58
    POSITIVE LOGITS
     forth
    1.44
    forth
    1.11
    bered
    1.06
    othe
    1.01
    oths
    1.00
    apy
    0.99
    ooo
    0.93
    oner
    0.92
    oooo
    0.90
     far
    0.85
    Act Density 0.042%

    No Known Activations