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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or locations, potentially related to a news event

    oai_token-act-pair · gpt-3.5-turbo

    references to the names "Morales" and "Morocco."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.87
    hower
    -0.83
    rophe
    -0.79
    ctive
    -0.73
    iago
    -0.72
    ting
    -0.71
    eq
    -0.70
    opia
    -0.68
    ysis
    -0.68
    ellation
    -0.67
    POSITIVE LOGITS
    rison
    0.77
     Morales
    0.75
    andom
    0.74
     livest
    0.71
    dyl
    0.70
    Mor
    0.69
    cow
    0.68
     Trails
    0.68
     occas
    0.67
     Reyes
    0.64
    Act Density 0.012%

    No Known Activations