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

    Neuronpedia

    INDEX
    Explanations

    instances of events happening for the first time in a while

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "since" followed by a time reference, indicating a timeline or historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.75
    amina
    -0.74
    abus
    -0.71
    bart
    -0.69
    iddler
    -0.68
    amount
    -0.66
    ereo
    -0.65
    Fight
    -0.64
    olan
    -0.64
    hack
    -0.64
    POSITIVE LOGITS
    rely
    1.12
    ĸļ
    1.08
     approving
    0.75
     1979
    0.73
     installing
    0.73
     1946
    0.73
     1961
    0.72
     1971
    0.71
     inception
    0.71
     1947
    0.71
    Act Density 0.051%

    No Known Activations