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

    Neuronpedia

    INDEX
    Explanations

    punctuated statements and lists of nominees or descriptions in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.83
    endpush
    -0.73
    InjectAttribute
    -0.72
     Савезне
    -0.66
    complexContent
    -0.66
    Erreferentziak
    -0.65
     становника
    -0.65
    OGND
    -0.65
    viewDidLoad
    -0.65
    KURZBESCHREIBUNG
    -0.63
    POSITIVE LOGITS
     Examples
    0.65
    antaranya
    0.65
    Examples
    0.63
     examples
    0.59
    landse
    0.52
    いくつか
    0.51
     например
    0.50
    例えば
    0.49
     include
    0.49
     EXAMPLES
    0.48
    Act Density 0.548%

    No Known Activations