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

    Neuronpedia

    INDEX
    Explanations

    dates and the word "then" in the context of referring to a specific point in time in past events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "then" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mson
    -0.72
    chy
    -0.71
    ting
    -0.68
     stalls
    -0.67
    toe
    -0.66
    endas
    -0.66
    orum
    -0.64
    ters
    -0.63
    mons
    -0.62
    icles
    -0.62
    POSITIVE LOGITS
    ©¶æ
    0.82
     proceeded
    0.78
    ħĭ
    0.76
    ŃĶ
    0.74
    Ń·
    0.68
    ñ
    0.67
    etheless
    0.65
    ãĥĥãĥī
    0.65
     remembered
    0.65
    isl
    0.65
    Act Density 0.051%

    No Known Activations