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

    Neuronpedia

    INDEX
    Explanations

    phrases related to surprise or revelation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surveillance and observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idian
    -0.68
    behind
    -0.68
    antine
    -0.63
    apo
    -0.63
     Sachs
    -0.59
     simultane
    -0.58
    ombs
    -0.58
    kson
    -0.55
    restrial
    -0.55
    stadt
    -0.54
    POSITIVE LOGITS
    illance
    0.74
    cliffe
    0.68
    pecting
    0.63
     Suite
    0.61
    Spread
    0.60
    fit
    0.58
    Condition
    0.58
    enegger
    0.57
    uber
    0.57
    onding
    0.55
    Act Density 0.123%

    No Known Activations