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

    Neuronpedia

    INDEX
    Explanations

    items related to data quality and evaluation metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.51
    twimg
    -0.46
    InitStruct
    -0.46
    IndentedString
    -0.44
     EconPapers
    -0.44
     CreateTagHelper
    -0.43
     AttributeSet
    -0.43
     хватает
    -0.42
    featureID
    -0.40
    JNIEnv
    -0.40
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.41
     Administrativna
    0.39
    perror
    0.36
    ésult
    0.36
    Lauf
    0.34
     visst
    0.34
    graphicx
    0.33
    ngdoc
    0.33
    GeneratedCode
    0.33
    withIdentifier
    0.33
    Act Density 0.952%

    No Known Activations