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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAlignment
    -0.82
    الصفحه
    -0.72
    jména
    -0.67
    ViewFeatures
    -0.67
    apunov
    -0.67
     resourceCulture
    -0.65
     CreateTagHelper
    -0.65
    BindingResult
    -0.64
     Réponses
    -0.64
    DispatchToProps
    -0.63
    POSITIVE LOGITS
     like
    1.62
     LIKE
    1.13
     unlike
    1.04
     Like
    1.03
    Like
    0.87
     liek
    0.86
     seperti
    0.83
    unlike
    0.83
    就像
    0.80
    就像是
    0.78
    Act Density 0.102%

    No Known Activations