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

    Neuronpedia

    INDEX
    Explanations

    terms related to reputation and public perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PostExecute
    -0.52
    awaiter
    -0.52
    thul
    -0.52
     kasarigan
    -0.51
    rix
    -0.49
    ố
    -0.48
    newcommand
    -0.48
     rendez
    -0.48
     Kir
    -0.47
    ya
    -0.45
    POSITIVE LOGITS
     Perceived
    0.87
     Considered
    0.87
     regarded
    0.85
     respected
    0.83
     perceived
    0.79
    idered
    0.79
    appreciated
    0.78
     unpopular
    0.76
     revered
    0.76
    considered
    0.75
    Act Density 0.388%

    No Known Activations