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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consent or acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Potter
    -0.70
    virons
    -0.69
    AdapterView
    -0.68
    Korn
    -0.67
     PrintWriter
    -0.66
     lot
    -0.65
    iVar
    -0.63
     Polk
    -0.62
     dran
    -0.61
    modium
    -0.61
    POSITIVE LOGITS
     accept
    1.63
     Accept
    1.62
     accepts
    1.55
     Accepting
    1.54
     ACCEPT
    1.48
     accepting
    1.47
     Acceptance
    1.46
     acceptance
    1.45
    Accept
    1.43
     accepted
    1.42
    Act Density 0.069%

    No Known Activations