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

    Neuronpedia

    INDEX
    Explanations

    informational content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "information" in various contexts, especially related to inquiries or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alone
    -0.77
    gg
    -0.69
    atos
    -0.69
    awar
    -0.66
    jug
    -0.66
     Parables
    -0.66
    kus
    -0.65
    irth
    -0.65
     Cats
    -0.65
    igham
    -0.64
    POSITIVE LOGITS
     glean
    1.03
     overload
    0.92
     retrieval
    0.91
     gathered
    0.82
     conveyed
    0.81
     dissemination
    0.81
     regarding
    0.80
     theoret
    0.78
    frame
    0.78
    arial
    0.78
    Act Density 0.040%

    No Known Activations