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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ever" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     linkovi
    -0.98
    MockBean
    -0.95
    TypedDataSet
    -0.93
    SharedDtor
    -0.93
    LabelTagHelper
    -0.92
    GenerationType
    -0.87
     GenerationType
    -0.86
     IndexPath
    -0.86
     <=",
    -0.84
     GetEnumerator
    -0.83
    POSITIVE LOGITS
     EVER
    0.75
     Ever
    0.69
     Everett
    0.67
    ver
    0.66
    iver
    0.66
    ever
    0.64
     wondered
    0.63
     ever
    0.60
    Ever
    0.60
     Evers
    0.58
    Act Density 0.030%

    No Known Activations