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

    Neuronpedia

    INDEX
    Explanations

    words related to moving on from specific topics or associations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases that suggest movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CB
    -0.69
    CF
    -0.68
    BAT
    -0.66
    wic
    -0.66
    four
    -0.66
    laughter
    -0.65
    among
    -0.65
    five
    -0.65
    Penn
    -0.64
    lot
    -0.64
    POSITIVE LOGITS
     concentrate
    1.19
     instead
    1.16
     replaced
    1.11
     Instead
    1.06
    Instead
    1.06
     replace
    1.05
     opting
    1.01
     revert
    1.01
     replaces
    0.99
     releg
    0.98
    Act Density 0.325%

    No Known Activations