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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating superiority or excellence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uten
    -0.15
    ilen
    -0.14
    ovi
    -0.14
    ãģĻãģĻ
    -0.14
    658
    -0.14
    év
    -0.14
    hua
    -0.13
    568
    -0.13
    ffect
    -0.13
    |array
    -0.13
    POSITIVE LOGITS
     breed
    0.41
     Breed
    0.35
     luck
    0.25
     breeds
    0.24
     bred
    0.24
     intentions
    0.23
     breeding
    0.21
     bunch
    0.20
    bre
    0.20
     class
    0.20
    Act Density 0.023%

    No Known Activations