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

    Neuronpedia

    INDEX
    Explanations

    pronouns and nouns related to other entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kris
    -0.68
     recess
    -0.66
     BJ
    -0.65
     commission
    -0.63
    âĢ¢âĢ¢
    -0.61
     Tours
    -0.60
     BDS
    -0.60
     BART
    -0.60
     Kahn
    -0.58
     Kenya
    -0.58
    POSITIVE LOGITS
    atically
    1.23
    redients
    1.13
    atic
    1.06
    adow
    1.01
    alian
    0.98
    auri
    0.96
    ption
    0.94
    cius
    0.94
    entials
    0.93
    adows
    0.92
    Act Density 0.029%

    No Known Activations