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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    letters or initials referring to people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skydragon
    -0.82
     Rebels
    -0.76
     Colleges
    -0.72
     Pastebin
    -0.69
     hereafter
    -0.66
     Cerberus
    -0.65
     nutshell
    -0.64
     hive
    -0.64
     downgrade
    -0.61
     Secondary
    -0.60
    POSITIVE LOGITS
    aryn
    1.23
    rika
    1.20
    icky
    1.20
    aryl
    1.19
    eryl
    1.19
    lyss
    1.13
    ileen
    1.12
    anya
    1.12
    ilda
    1.10
    resa
    1.10
    Act Density 0.145%

    No Known Activations