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

    Neuronpedia

    INDEX
    Explanations

    concepts related to alienation and isolation

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

    isolation and separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     improved
    -0.30
     den
    -0.30
     run
    -0.30
     equipment
    -0.29
    improved
    -0.28
     comerci
    -0.27
     Gen
    -0.26
    probability
    -0.26
     gen
    -0.26
     performance
    -0.26
    POSITIVE LOGITS
     myſelf
    0.75
     isolamento
    0.72
     isolato
    0.71
    featureID
    0.68
     isolating
    0.67
     isolation
    0.67
     ſta
    0.67
    ſelves
    0.65
     Trennung
    0.65
     ſch
    0.65
    Act Density 0.039%

    No Known Activations