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

    Neuronpedia

    INDEX
    Explanations

    things related to specific instructions or directions

    oai_token-act-pair · gpt-3.5-turbo

    the word "To" indicating purpose or intent in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.71
     nets
    -0.69
    itiz
    -0.66
     drops
    -0.65
    hops
    -0.65
     forg
    -0.63
     wipes
    -0.61
     diapers
    -0.60
     taps
    -0.60
     clut
    -0.59
    POSITIVE LOGITS
    ilet
    1.24
     summarize
    1.05
     reiterate
    0.94
    oru
    0.89
     clarify
    0.89
    ffee
    0.89
    ppings
    0.87
    pping
    0.84
    aru
    0.83
     celebrate
    0.81
    Act Density 0.052%

    No Known Activations