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

    Neuronpedia

    INDEX
    Explanations

    conjunctions or transitional phrases

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "and so" or variations indicating continuation or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alpine
    -0.58
     Federal
    -0.54
    efe
    -0.54
     Burg
    -0.53
     nic
    -0.52
     MPH
    -0.52
     Depth
    -0.52
    WN
    -0.52
     Talking
    -0.52
     Swanson
    -0.51
    POSITIVE LOGITS
     forth
    1.18
    apy
    1.10
    bered
    1.08
    oths
    1.07
    othe
    1.06
    oner
    1.06
    ooo
    0.96
    oooo
    0.93
    othes
    0.92
    aps
    0.87
    Act Density 0.057%

    No Known Activations