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

    Neuronpedia

    INDEX
    Explanations

    detailed information or facts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "information."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gg
    -0.78
    jug
    -0.75
    alone
    -0.73
    kus
    -0.69
    awar
    -0.68
    irth
    -0.67
    ggles
    -0.67
     Parables
    -0.66
    warm
    -0.64
     sunny
    -0.62
    POSITIVE LOGITS
    afety
    0.86
     glean
    0.85
     retrieval
    0.84
    ãĤ±
    0.84
    ãĥĨ
    0.82
     overload
    0.81
     information
    0.81
    anooga
    0.80
     theoret
    0.80
    llor
    0.77
    Act Density 0.035%

    No Known Activations