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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases ending with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude or summarize ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icz
    -0.81
     quir
    -0.79
     volunte
    -0.78
     satell
    -0.76
     corrid
    -0.73
     tremend
    -0.71
     subur
    -0.71
    ikuman
    -0.70
     carbohyd
    -0.70
     boun
    -0.69
    POSITIVE LOGITS
     Also
    1.23
     Additionally
    1.20
     Includes
    1.10
     However
    1.07
     Continue
    1.07
    aspx
    1.04
     Otherwise
    1.04
     Learn
    1.01
     Meanwhile
    1.00
     Furthermore
    1.00
    Act Density 0.563%

    No Known Activations