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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or designations tied to measurements or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbing
    -0.18
    Äħd
    -0.16
    uger
    -0.15
    ConfigurationException
    -0.15
    }elseif
    -0.15
    ãĥ³ãĥĢ
    -0.15
    ogh
    -0.15
    .cfg
    -0.14
    ugu
    -0.14
    igit
    -0.14
    POSITIVE LOGITS
     Pro
    0.26
     Dist
    0.23
    Dist
    0.22
    Pro
    0.21
     DIST
    0.21
    dist
    0.20
     dist
    0.20
    DIST
    0.19
     District
    0.19
     Camp
    0.18
    Act Density 0.034%

    No Known Activations