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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions and personal achievements

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions used to connect thoughts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.70
    azeera
    -0.67
    Leaks
    -0.66
    owitz
    -0.65
    payer
    -0.64
    ajor
    -0.64
    hor
    -0.63
    bold
    -0.62
    ential
    -0.62
    RNA
    -0.61
    POSITIVE LOGITS
     secondly
    1.32
     then
    1.11
    romeda
    1.07
     thus
    1.07
     THEN
    1.06
     hence
    1.02
     luckily
    1.02
     whilst
    0.98
     consequently
    0.95
    ersen
    0.95
    Act Density 0.477%

    No Known Activations