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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal internal conflict or emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozor
    -0.15
    elli
    -0.15
     наÑģÑĤ
    -0.15
    важ
    -0.14
    iddet
    -0.14
    ï¼Īå¹³æĪIJ
    -0.14
     Blind
    -0.14
     Sight
    -0.13
    avenous
    -0.13
    ëĮĢë¡ľ
    -0.13
    POSITIVE LOGITS
     gas
    0.27
     gro
    0.26
     wonder
    0.26
    gro
    0.21
     cr
    0.21
     invol
    0.21
     inward
    0.21
     Wonder
    0.20
     immediately
    0.19
     perk
    0.19
    Act Density 0.352%

    No Known Activations