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

    Neuronpedia

    INDEX
    Explanations

    terms related to acceptance and rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ervoor
    -0.50
     electricity
    -0.46
     affairs
    -0.46
     שוליים
    -0.46
     the
    -0.46
     about
    -0.45
    DIRECTION
    -0.43
     propertyName
    -0.43
     query
    -0.42
     OPERATION
    -0.42
    POSITIVE LOGITS
     accept
    1.21
     accepts
    1.15
     Accept
    1.13
     accepted
    1.09
    Accept
    1.09
     Accepted
    1.09
     ACCEPT
    1.06
    accepted
    1.05
     Accepting
    1.04
    Accepted
    1.02
    Act Density 0.234%

    No Known Activations