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

    Neuronpedia

    INDEX
    Explanations

    formatted linguistic characters

    oai_token-act-pair · gpt-3.5-turbo

    indications of online discussions or community interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pione
    -0.97
     brid
    -0.93
    ¥ŀ
    -0.90
     carbohyd
    -0.87
     coral
    -0.86
     grapp
    -0.85
     subur
    -0.84
    ©¶æ
    -0.84
     increasingly
    -0.84
     enriched
    -0.83
    POSITIVE LOGITS
    And
    1.93
    That
    1.83
    Which
    1.83
    But
    1.78
    Then
    1.77
    They
    1.77
    Sounds
    1.75
    Again
    1.74
    Yep
    1.74
    Here
    1.73
    Act Density 0.467%

    No Known Activations