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

    Neuronpedia

    INDEX
    Explanations

    names of entities related to power and leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
     Zub
    -0.19
    DEX
    -0.19
    iais
    -0.18
    ardown
    -0.16
    ymi
    -0.16
    ivé
    -0.15
    ÃŃas
    -0.15
    arpa
    -0.15
     Turnbull
    -0.15
    POSITIVE LOGITS
    EW
    0.15
     McD
    0.15
     Partners
    0.15
    ädchen
    0.14
     пÑĢез
    0.14
    ebin
    0.14
    owi
    0.14
    _partner
    0.14
     partners
    0.13
    ince
    0.13
    Act Density 0.007%

    No Known Activations