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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and quality

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or strong statements about conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chuk
    -0.76
     Previous
    -0.64
    tz
    -0.63
    ibrary
    -0.62
     Bangl
    -0.61
    imental
    -0.60
    atown
    -0.60
    xia
    -0.60
    historic
    -0.59
     Tir
    -0.58
    POSITIVE LOGITS
     accordingly
    1.09
     consequently
    1.03
     thereafter
    0.95
     alike
    0.88
     therein
    0.80
     thereof
    0.76
     promptly
    0.74
     therefore
    0.74
     certainly
    0.73
     afterward
    0.72
    Act Density 0.519%

    No Known Activations