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

    Neuronpedia

    INDEX
    Explanations

    expressions related to guarantees or assurances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gi
    -0.18
    aks
    -0.15
    lendir
    -0.14
    uC
    -0.14
    illiseconds
    -0.14
    spawn
    -0.14
    خاÙĨÙĩ
    -0.14
    sk
    -0.14
    ugg
    -0.14
     меÑĤоÑİ
    -0.14
    POSITIVE LOGITS
    anteed
    0.26
    ably
    0.26
     against
    0.23
    bsolute
    0.21
    ing
    0.20
    /prom
    0.19
    Against
    0.18
     safe
    0.18
     minimum
    0.18
    antee
    0.18
    Act Density 0.040%

    No Known Activations