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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "But" and similar conjunctions signaling shifts in argument or contrast

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

    following "But" or similar conjunctions

    np_acts-logits-general · gemini-2.0-flash

    but, then, later, of, there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Griffin
    -0.60
    FactoryBean
    -0.59
    dib
    -0.59
    BoxShadow
    -0.56
     חיצוניים
    -0.56
     Engel
    -0.53
     fa
    -0.52
    freiheit
    -0.51
    Šaltiniai
    -0.51
    Griffin
    -0.51
    POSITIVE LOGITS
    AsUp
    1.03
     تضيفلها
    0.83
    MeasureSpec
    0.75
    ſelves
    0.72
    ſelf
    0.70
     XNUMX
    0.69
     houſe
    0.68
     eſt
    0.68
     auroit
    0.67
     Justine
    0.66
    Act Density 0.712%

    No Known Activations