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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.76
    bda
    -0.66
    natureconservancy
    -0.65
    Network
    -0.65
    BAT
    -0.65
    Free
    -0.64
    pee
    -0.64
    Stone
    -0.62
    rain
    -0.62
    Nit
    -0.62
    POSITIVE LOGITS
     onwards
    1.21
     onward
    1.06
     thence
    0.97
     thus
    0.96
     then
    0.94
     hence
    0.91
     thereafter
    0.90
     consequently
    0.89
     thereby
    0.85
     therefore
    0.84
    Act Density 0.191%

    No Known Activations