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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating division or categorization of subjects and objects

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

    division or separation

    np_acts-logits-general · gemini-2.0-flash

    divided into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ucket
    -0.55
     فريبيس
    -0.55
    Према
    -0.53
    ratore
    -0.52
     Eugenia
    -0.50
    worths
    -0.48
     AssemblyTitle
    -0.47
     محفوظة
    -0.46
    nteral
    -0.46
     Thackeray
    -0.46
    POSITIVE LOGITS
     divided
    2.27
     split
    2.00
     divide
    1.99
    divided
    1.95
     Divided
    1.94
     divides
    1.82
     Divide
    1.76
     dividing
    1.75
     Split
    1.75
    Split
    1.71
    Act Density 0.476%

    No Known Activations