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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "surreal" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viders
    -0.17
    itele
    -0.16
     reuse
    -0.15
    ska
    -0.15
    /REC
    -0.15
    rote
    -0.14
     prox
    -0.14
    som
    -0.14
    osemite
    -0.14
    Türkiye
    -0.14
    POSITIVE LOGITS
    nder
    0.28
     Surre
    0.25
     surre
    0.23
    alist
    0.23
    URRE
    0.20
    urre
    0.19
    NDER
    0.18
    rend
    0.17
    ault
    0.17
     surrender
    0.17
    Act Density 0.010%

    No Known Activations