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

    Neuronpedia

    INDEX
    Explanations

    phrases with prepositions indicating relationships or connections

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

    following prepositions and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.69
    ftagPool
    -0.67
     فريبيس
    -0.64
     BoxFit
    -0.56
    󠁮
    -0.54
    setVerticalGroup
    -0.53
     يتيمه
    -0.51
    IntoConstraints
    -0.50
     виправивши
    -0.49
    transQ
    -0.49
    POSITIVE LOGITS
    #
    0.39
    Życiorys
    0.37
    ContentAsync
    0.33
     ser
    0.33
     marke
    0.31
    説
    0.31
     kró
    0.30
     inc
    0.30
     ¶
    0.30
    降
    0.29
    Act Density 0.267%

    No Known Activations