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

    Neuronpedia

    INDEX
    Explanations

    the word "alone" as a standalone concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a sense of not being alone or concepts related to isolation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hut
    -0.65
    atu
    -0.63
     Junk
    -0.62
     Skydragon
    -0.62
     wed
    -0.61
    iet
    -0.58
     ****
    -0.57
    mit
    -0.57
     Fallen
    -0.56
    hu
    -0.55
    POSITIVE LOGITS
    otti
    0.69
     accus
    0.69
    oshenko
    0.68
    gre
    0.66
     skeptics
    0.65
    gebra
    0.64
    Compl
    0.63
    Lens
    0.62
     fortun
    0.61
    ingen
    0.61
    Act Density 0.059%

    No Known Activations