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

    Neuronpedia

    INDEX
    Explanations

    concepts related to power and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fjspx
    -0.71
    StoryboardSegue
    -0.69
     AspNetCore
    -0.63
    StackSize
    -0.59
     Deckel
    -0.58
    verwijspagina
    -0.53
    soever
    -0.52
     fasti
    -0.51
    NOST
    -0.50
     ويكيپيديا
    -0.50
    POSITIVE LOGITS
     power
    1.88
    power
    1.66
     Power
    1.59
     POWER
    1.55
    POWER
    1.49
    Power
    1.49
     powers
    1.38
    powers
    1.35
     puissance
    1.30
    powerful
    1.29
    Act Density 0.270%

    No Known Activations