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

    Neuronpedia

    INDEX
    Explanations

    information-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    emphasis on the concept of information and its various forms and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.69
    ModLoader
    -0.68
     Parables
    -0.66
    interstitial
    -0.63
    kus
    -0.62
    igl
    -0.62
    gg
    -0.62
    engeance
    -0.61
    itan
    -0.61
    dog
    -0.61
    POSITIVE LOGITS
     glean
    1.16
     overload
    1.07
     gathered
    1.06
     regarding
    1.01
     pertaining
    1.01
     about
    1.00
     concerning
    0.94
     theoret
    0.93
     retrieval
    0.93
     conveyed
    0.92
    Act Density 0.048%

    No Known Activations