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

    Neuronpedia

    INDEX
    Explanations

    words related to positivity and elegance

    oai_token-act-pair · gpt-3.5-turbo

    the presence of structured text or document boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odcast
    -0.77
    sbm
    -0.76
    gets
    -0.75
    wat
    -0.74
    ummer
    -0.74
    wives
    -0.74
    ETS
    -0.73
    hov
    -0.73
    ESE
    -0.72
    wic
    -0.70
    POSITIVE LOGITS
     creativity
    1.08
     generosity
    0.95
     solitude
    0.95
     responsiveness
    0.95
     nuance
    0.94
     heroism
    0.94
     persever
    0.93
     professionalism
    0.93
     dignity
    0.92
     admiration
    0.92
    Act Density 0.322%

    No Known Activations