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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases indicating duration or specific years

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and conjunctions that relate to time and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.74
    agra
    -0.55
     [*
    -0.55
     destro
    -0.54
     Jagu
    -0.51
    Ban
    -0.49
    egal
    -0.49
    erenn
    -0.49
     horizont
    -0.49
    _.
    -0.49
    POSITIVE LOGITS
    ibles
    0.50
    anta
    0.50
    thood
    0.50
    lining
    0.48
     CentOS
    0.48
    reach
    0.48
     Xperia
    0.47
     nutshell
    0.47
    displayText
    0.47
     Seasons
    0.46
    Act Density 0.620%

    No Known Activations