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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal assessments or opinions about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceive
    -0.70
     childbirth
    -0.64
     Tud
    -0.63
    face
    -0.62
    cribed
    -0.62
     bir
    -0.61
     Generation
    -0.61
     glac
    -0.61
     ensured
    -0.60
    ared
    -0.59
    POSITIVE LOGITS
    ById
    1.00
     effic
    0.81
     objectionable
    0.76
    bleacher
    0.75
    AppData
    0.74
    )</
    0.73
     è£ıè
    0.72
     elusive
    0.71
     bugs
    0.70
    CVE
    0.70
    Act Density 0.280%

    No Known Activations