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

    Neuronpedia

    INDEX
    Explanations

    quotes or paraphrases that express opinions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text enclosed in quotation marks

    np_acts-logits-general · gemini-2.0-flash

    after quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.68
     betweenstory
    -0.67
     aktivitet
    -0.65
     thyself
    -0.65
     themſelves
    -0.62
     насељу
    -0.61
     χρήση
    -0.61
    fromnode
    -0.61
     myſelf
    -0.60
     cauſe
    -0.60
    POSITIVE LOGITS
    '),
    0.78
     very
    0.76
    absolutely
    0.72
     absolutely
    0.71
    very
    0.70
    "):
    0.70
    ']))
    0.70
    "){
    0.69
    '){
    0.68
    "),
    0.68
    Act Density 0.168%

    No Known Activations