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

    Neuronpedia

    INDEX
    Explanations

    decontextualized text with formatting errors

    oai_token-act-pair · gpt-3.5-turbo

    references to limitations or conditions affecting experiences or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Britann
    -0.69
     Ops
    -0.68
     Reloaded
    -0.68
     Directory
    -0.64
     Examination
    -0.64
     penned
    -0.61
     Nutr
    -0.60
     Scotia
    -0.60
     HSBC
    -0.60
     gauge
    -0.59
    POSITIVE LOGITS
    too
    1.05
    great
    1.02
    selves
    0.98
    mom
    0.98
    warm
    0.95
    same
    0.95
    dead
    0.93
    recomm
    0.92
    wrong
    0.90
    being
    0.90
    Act Density 0.076%

    No Known Activations