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

    Neuronpedia

    INDEX
    Explanations

    terms related to segregation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enty
    -0.17
    itting
    -0.15
    onica
    -0.15
    icket
    -0.15
     GA
    -0.14
    lify
    -0.14
    exterity
    -0.14
    set
    -0.14
     Buckley
    -0.14
    lo
    -0.13
    POSITIVE LOGITS
    ecast
    0.16
    /{$
    0.16
    orst
    0.16
    AFX
    0.15
    stad
    0.14
    apixel
    0.14
    erin
    0.14
     Hor
    0.14
    arb
    0.14
    erais
    0.13
    Act Density 0.004%

    No Known Activations