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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate hearsay or personal anecdotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.75
     springfox
    -0.73
    IsContent
    -0.72
    ponses
    -0.70
    ergies
    -0.70
    IUrlHelper
    -0.70
    setVerticalGroup
    -0.69
     externi
    -0.68
    InjectAttribute
    -0.67
    ViewFeatures
    -0.66
    POSITIVE LOGITS
    听说
    0.71
     rumors
    0.64
     rumor
    0.62
     rumored
    0.62
     told
    0.57
     rumours
    0.53
     rumoured
    0.51
     advised
    0.50
     claims
    0.50
     idea
    0.49
    Act Density 0.283%

    No Known Activations