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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     denn
    -0.61
     Einwilligung
    -0.57
    <()>
    -0.56
    Eileen
    -0.56
     Numerade
    -0.56
    ksesta
    -0.55
    BindingSource
    -0.55
    ocarditis
    -0.55
    oas
    -0.54
     myö
    -0.53
    POSITIVE LOGITS
     таки
    0.71
    دانشنامهٔ
    0.70
    nościo
    0.70
    InvalidProtocol
    0.68
     right
    0.66
    StoreMessageInfo
    0.64
    λια
    0.61
    zeera
    0.61
    elemField
    0.60
    :✨
    0.60
    Act Density 0.128%

    No Known Activations