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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases relating to spatial relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to tribes and tribal affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.62
    utters
    -0.61
     stuff
    -0.61
    velt
    -0.60
     Imran
    -0.58
    "}
    -0.57
     here
    -0.55
    estern
    -0.54
    stuff
    -0.54
    amily
    -0.53
    POSITIVE LOGITS
     guiActiveUnfocused
    0.75
     expire
    0.67
     undergoing
    0.65
    their
    0.61
     breaching
    0.60
    Laun
    0.58
     wishing
    0.58
     achieving
    0.57
     launching
    0.57
     registering
    0.57
    Act Density 1.214%

    No Known Activations