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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities, particularly names containing "Tor"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.56
    webElementXpaths
    -0.52
    Jeografia
    -0.51
    HasAnnotation
    -0.47
    cshtml
    -0.47
     CanadaChoose
    -0.45
     Italijanski
    -0.45
    显
    -0.44
     Reverso
    -0.44
     Golfo
    -0.44
    POSITIVE LOGITS
    Tor
    0.74
     Tor
    0.73
    tor
    0.70
     tor
    0.69
     Ren
    0.66
    Ren
    0.62
     TOR
    0.59
    TOR
    0.57
     Roman
    0.54
    Sab
    0.54
    Act Density 0.535%

    No Known Activations