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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating existence or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aversable
    -0.16
    éĿ
    -0.16
    spiel
    -0.15
     Ade
    -0.14
    zahl
    -0.14
    gewater
    -0.14
    boxed
    -0.14
    oods
    -0.14
     ade
    -0.14
    à¹īà¸ĩ
    -0.13
    POSITIVE LOGITS
    sik
    0.15
    ppo
    0.15
    .scalablytyped
    0.15
    assi
    0.14
    avad
    0.14
    ospace
    0.14
    ucz
    0.14
    avity
    0.14
    iet
    0.13
    regor
    0.13
    Act Density 0.441%

    No Known Activations