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

    Neuronpedia

    INDEX
    Explanations

    versions and acronyms of the term "RS"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific system or classification indicated by "RS" along with their associated values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Contra
    -0.80
    leck
    -0.74
    framework
    -0.74
     Samoa
    -0.73
    enegger
    -0.73
     Antarctic
    -0.73
    aneously
    -0.70
    renheit
    -0.69
    rities
    -0.69
    berman
    -0.68
    POSITIVE LOGITS
    RS
    1.18
    VP
    0.98
    ACK
    0.92
    acks
    0.87
    232
    0.86
    ESSION
    0.85
    RP
    0.84
    ocial
    0.83
    OCK
    0.83
    OURCE
    0.81
    Act Density 0.010%

    No Known Activations