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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" in various contexts

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

    so please

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cref
    -0.52
    EndContext
    -0.44
    bootstrapcdn
    -0.39
    Билгалдахарш
    -0.34
     adrift
    -0.34
    Dijo
    -0.34
    rån
    -0.33
    Dramatic
    -0.33
    mería
    -0.33
    ungguhnya
    -0.32
    POSITIVE LOGITS
    MemoryWarning
    0.97
    istoitu
    0.63
    المناصب
    0.57
    isContained
    0.49
    DotNetBar
    0.49
     humeur
    0.48
     houſe
    0.47
    ſelves
    0.46
    embre
    0.46
    पया
    0.45
    Act Density 0.010%

    No Known Activations