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

    Neuronpedia

    INDEX
    Explanations

    phrases related to feedback

    oai_token-act-pair · gpt-3.5-turbo

    references to user feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neys
    -0.81
    chin
    -0.72
    asar
    -0.72
    amina
    -0.68
    adem
    -0.67
    ffe
    -0.64
    frey
    -0.63
    eni
    -0.63
    readable
    -0.62
    nova
    -0.61
    POSITIVE LOGITS
     feedback
    1.13
     loops
    0.91
     Feedback
    0.89
     testers
    0.87
     assurance
    0.81
    urai
    0.74
     loop
    0.73
    ible
    0.69
    isson
    0.68
    ãĤī
    0.65
    Act Density 0.024%

    No Known Activations