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

    Neuronpedia

    INDEX
    Explanations

    keywords related to cookies and user experience on websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bound
    -0.15
     Raw
    -0.14
    Ngh
    -0.14
     Flo
    -0.14
    -bound
    -0.14
     err
    -0.14
    rup
    -0.13
     Peripheral
    -0.13
     Err
    -0.13
     slack
    -0.13
    POSITIVE LOGITS
    remember
    0.21
     remembered
    0.21
     remember
    0.21
     remembering
    0.20
     remembers
    0.20
    Remember
    0.19
     Remember
    0.19
    è®°
    0.16
     anon
    0.16
     tailor
    0.15
    Act Density 0.021%

    No Known Activations