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

    Neuronpedia

    INDEX
    Explanations

    time and location references for events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     slapping
    -0.81
     utter
    -0.78
     lately
    -0.76
     mang
    -0.76
     abandoning
    -0.75
     slowing
    -0.74
     forestry
    -0.73
     matured
    -0.73
     prototyp
    -0.73
     shrinking
    -0.73
    POSITIVE LOGITS
     Tickets
    1.59
    Tickets
    1.39
     Afterwards
    1.25
     Admission
    1.23
     Additionally
    1.21
     Dates
    1.21
     Participants
    1.20
     Proceed
    1.19
    <|endoftext|>
    1.19
     Doors
    1.17
    Act Density 0.317%

    No Known Activations