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

    Neuronpedia

    INDEX
    Explanations

    discussions related to physical properties and conditions like temperature, voltage, and conditions for survival

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.75
    ERAL
    -0.73
    inav
    -0.73
    onnaissance
    -0.69
    ookie
    -0.69
    emonium
    -0.68
    pedia
    -0.67
    Scroll
    -0.66
    ossom
    -0.65
     Letters
    -0.64
    POSITIVE LOGITS
     deemed
    1.07
     not
    1.04
    nt
    1.03
     sufficiently
    0.99
     unavailable
    0.95
     unable
    0.94
     properly
    0.92
     configured
    0.91
     judged
    0.91
     located
    0.91
    Act Density 0.193%

    No Known Activations