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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hybrid concepts or things that combine different elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anskje
    -0.52
     Hentet
    -0.52
     Scho
    -0.51
     Италијани
    -0.48
    scho
    -0.47
    INERY
    -0.47
     Big
    -0.47
    ]^{-
    -0.46
    酰
    -0.46
    pragma
    -0.46
    POSITIVE LOGITS
     mixtures
    1.03
     hybrids
    1.00
    alert
    0.99
    hybrid
    0.98
     hybrid
    0.97
     Mixture
    0.96
    Mixture
    0.94
     mixture
    0.94
     mix
    0.94
    Hybrid
    0.93
    Act Density 0.105%

    No Known Activations