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

    Neuronpedia

    INDEX
    Explanations

    scientific research-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to scientific discovery and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.68
    Attributes
    -0.67
    washer
    -0.64
     constituent
    -0.64
    Interstitial
    -0.64
    Mega
    -0.62
    FY
    -0.62
    HAHA
    -0.62
     alcoholic
    -0.61
     Presidency
    -0.61
    POSITIVE LOGITS
    ateurs
    0.95
     alike
    0.92
    vae
    0.89
     uncover
    0.84
    raq
    0.84
     speculate
    0.82
     convened
    0.79
     cautioned
    0.78
    hran
    0.77
     delighted
    0.75
    Act Density 0.442%

    No Known Activations