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

    Neuronpedia

    INDEX
    Explanations

    references to work experience and expertise in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocator
    -0.15
    ota
    -0.15
    allis
    -0.15
    zeitig
    -0.15
    otron
    -0.15
    ELLOW
    -0.14
    OTA
    -0.14
    avic
    -0.14
    _depend
    -0.14
    .dep
    -0.14
    POSITIVE LOGITS
     gained
    0.25
     across
    0.22
     working
    0.22
     acquired
    0.22
     acum
    0.21
     dating
    0.21
     accumulated
    0.20
     hon
    0.20
     Span
    0.19
    working
    0.18
    Act Density 0.087%

    No Known Activations