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

    Neuronpedia

    INDEX
    Explanations

    instances where the subject is reflecting on past experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal reflections and self-references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfocusedRange
    -0.62
     preserves
    -0.62
     winners
    -0.60
     endif
    -0.59
    orate
    -0.58
    Regardless
    -0.58
    ãĤ¼
    -0.58
     applause
    -0.56
     abdom
    -0.56
     none
    -0.56
    POSITIVE LOGITS
    'm
    1.19
    've
    0.98
     arrived
    0.92
     started
    0.91
     asked
    0.87
     interviewed
    0.87
     myself
    0.87
     woke
    0.86
     first
    0.84
     hear
    0.83
    Act Density 0.079%

    No Known Activations