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

    Neuronpedia

    INDEX
    Explanations

    phrases related to familial relationships and identity

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

    Follows a common word (a, will, back, be, it, can)

    np_acts-logits-general · gemini-2.0-flash

    future possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.98
     חיצוניים
    -0.89
     saites
    -0.89
    IsContent
    -0.89
     NSCoder
    -0.87
    twimg
    -0.85
     intptr
    -0.84
    ponses
    -0.78
     للاسماء
    -0.76
    tanleria
    -0.76
    POSITIVE LOGITS
     por
    0.48
     s
    0.48
     met
    0.41
     ten
    0.40
     bad
    0.37
     π
    0.36
     mu
    0.35
    por
    0.35
     unter
    0.35
     e
    0.35
    Act Density 0.053%

    No Known Activations