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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey the concept of effect or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.70
     Haydn
    -0.68
    HasAnnotation
    -0.66
    TestingModule
    -0.64
     <<<<<<<<<<<<<<
    -0.62
     encontre
    -0.62
    NameInMap
    -0.61
     تضيفلها
    -0.60
    BagConstraints
    -0.59
    bootstrapcdn
    -0.59
    POSITIVE LOGITS
    相当于
    0.83
     basically
    0.74
    basically
    0.73
     essentially
    0.72
    Essentially
    0.72
    Basically
    0.70
    essentially
    0.69
     jakby
    0.66
    就像是
    0.65
     Basically
    0.65
    Act Density 0.290%

    No Known Activations