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

    Neuronpedia

    INDEX
    Explanations

    terms related to acceptance and rejection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propertyName
    -0.48
     about
    -0.44
     Pang
    -0.43
     the
    -0.42
     electricity
    -0.41
     middleware
    -0.41
     ISNI
    -0.40
     ammunition
    -0.40
     phy
    -0.40
     farming
    -0.39
    POSITIVE LOGITS
     accept
    1.98
     accepted
    1.86
     accepts
    1.84
     Accept
    1.80
    Accept
    1.78
     ACCEPT
    1.78
     acceptance
    1.77
     Accepted
    1.72
     accepting
    1.69
     Accepting
    1.68
    Act Density 0.126%

    No Known Activations