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

    Neuronpedia

    INDEX
    Explanations

    comparisons or correlations between different concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "so" in various contexts, indicating a relationship or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
     Bastard
    -0.60
    Got
    -0.58
     nic
    -0.56
    erness
    -0.55
     STD
    -0.54
    gie
    -0.54
    intosh
    -0.54
     Estimated
    -0.52
     presentation
    -0.52
    POSITIVE LOGITS
    oner
    1.10
    bered
    1.03
    apy
    0.92
    assi
    0.86
    oths
    0.86
    othes
    0.84
    arer
    0.84
     far
    0.83
     much
    0.81
    vere
    0.80
    Act Density 0.102%

    No Known Activations