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

    Neuronpedia

    INDEX
    Explanations

    sentences containing contractions (e.g., "it's", "that's") and possessive forms (e.g., "people's", "car's")

    oai_token-act-pair · gpt-3.5-turbo

    affirmations and statements of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.85
    arbon
    -0.84
    EStream
    -0.74
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
    erning
    -0.74
    onds
    -0.72
    interstitial
    -0.70
    velop
    -0.68
    20439
    -0.66
    estones
    -0.66
    POSITIVE LOGITS
     bullshit
    1.14
     irrelevant
    1.12
     okay
    1.10
     alright
    1.10
     ok
    1.08
     ridiculous
    1.07
     pointless
    1.07
     disrespectful
    1.04
     unacceptable
    1.04
     fine
    1.01
    Act Density 0.182%

    No Known Activations