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

    Neuronpedia

    INDEX
    Explanations

    specific time or date indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucid
    -0.48
    äch
    -0.45
     herunter
    -0.45
    ixante
    -0.45
     físicas
    -0.43
    groupName
    -0.43
     println
    -0.43
    cdnjs
    -0.43
     slightest
    -0.43
     sufficiente
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.75
     NSCoder
    0.72
    aryen
    0.72
    ########.
    0.69
     betweenstory
    0.65
     OMIT
    0.62
     estekak
    0.61
     oprot
    0.60
    EndInit
    0.59
    NOPQRST
    0.58
    Act Density 0.034%

    No Known Activations