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

    Neuronpedia

    INDEX
    Explanations

    discussions about comments and interactions in online forums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.89
    rungsseite
    -0.85
    WebElementEntity
    -0.82
     surla
    -0.82
    verwijspagina
    -0.80
     AssemblyTitle
    -0.72
     snippetHide
    -0.68
    homonymie
    -0.67
    يكب
    -0.66
    rrggbb
    -0.65
    POSITIVE LOGITS
    user
    0.39
     chill
    0.38
     who
    0.36
     you
    0.35
     lady
    0.34
    who
    0.34
     laughing
    0.33
     choking
    0.33
     Freitas
    0.32
     sticking
    0.32
    Act Density 0.022%

    No Known Activations