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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and duration

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and conjunctions within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.81
    ħĭ
    -0.79
    eele
    -0.76
    asma
    -0.68
    Amb
    -0.67
    irie
    -0.67
    eming
    -0.66
    ForgeModLoader
    -0.66
    eus
    -0.65
    Platform
    -0.65
    POSITIVE LOGITS
     culminating
    0.92
     totaling
    0.84
     culmin
    0.82
    depending
    0.82
     counting
    0.79
     depending
    0.77
     consecut
    0.74
     exhausting
    0.73
     accumulating
    0.68
     spanning
    0.68
    Act Density 0.364%

    No Known Activations