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

    Neuronpedia

    INDEX
    Explanations

    references to toxic spells or abilities in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GetEnumerator
    -0.69
     nonatomic
    -0.52
    RegistryLite
    -0.48
    ゴリー
    -0.47
    mög
    -0.47
     createSprite
    -0.46
    mær
    -0.45
     Marietta
    -0.45
    usercontent
    -0.44
    Infan
    -0.44
    POSITIVE LOGITS
    protoimpl
    0.64
     AssemblyTitle
    0.64
    Descripció
    0.60
    SequentialGroup
    0.58
    tvguidetime
    0.57
    <bos>
    0.57
     ftill
    0.55
    JsonHelper
    0.54
     correctes
    0.53
    헌
    0.53
    Act Density 0.187%

    No Known Activations