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

    Neuronpedia

    INDEX
    Explanations

    references to home or domestic settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thon
    -0.15
    haus
    -0.15
     Shepard
    -0.14
     Herman
    -0.14
    æİĽ
    -0.14
    instein
    -0.14
    orage
    -0.14
    izens
    -0.14
    ripe
    -0.14
    森
    -0.14
    POSITIVE LOGITS
     /
    0.17
    arrow
    0.16
     arrow
    0.15
    ild
    0.15
     breadcrumb
    0.15
     `/
    0.15
    ELLOW
    0.15
     page
    0.15
    -Encoding
    0.15
    zig
    0.14
    Act Density 0.004%

    No Known Activations