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

    Neuronpedia

    INDEX
    Explanations

    words related to security measures and technical functions

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to safety, security, and functionality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &
    -0.70
     AND
    -0.70
     et
    -0.69
    and
    -0.68
     and
    -0.67
    ModLoader
    -0.65
    And
    -0.64
    &
    -0.63
    ipel
    -0.62
     or
    -0.62
    POSITIVE LOGITS
     alike
    1.41
     respectively
    0.87
     thereof
    0.82
    depending
    0.70
     aspects
    0.69
     sectors
    0.65
     industries
    0.63
    SPONSORED
    0.63
     characterize
    0.63
     pertaining
    0.62
    Act Density 0.468%

    No Known Activations