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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    specific names and references potentially related to identities or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jere
    -1.17
    TY
    -0.85
     NEO
    -0.85
    JS
    -0.83
     Jem
    -0.81
    Jenn
    -0.79
     Jess
    -0.78
    Jere
    -0.78
     Ja
    -0.77
    Ja
    -0.77
    POSITIVE LOGITS
    °
    0.88
    irc
    0.81
     McCarthy
    0.78
    abre
    0.76
     crabs
    0.75
     crab
    0.75
    pur
    0.73
    abb
    0.72
    onga
    0.72
     Pett
    0.71
    Act Density 0.652%

    No Known Activations