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

    Neuronpedia

    INDEX
    Explanations

    words related to transitions or sequences of events

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and connecting words that indicate relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.87
     hardest
    -0.75
     referen
    -0.75
     rare
    -0.74
     calming
    -0.73
     warr
    -0.73
     hard
    -0.72
    £ı
    -0.71
     recession
    -0.71
     exha
    -0.71
    POSITIVE LOGITS
    iste
    0.82
    pad
    0.81
    imi
    0.81
    illian
    0.81
    lys
    0.81
    atis
    0.80
    tec
    0.80
    hess
    0.80
    pedia
    0.80
    vier
    0.79
    Act Density 0.358%

    No Known Activations