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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time periods or temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overview
    -0.19
     Overview
    -0.18
    overview
    -0.18
    Overview
    -0.15
    oplevel
    -0.15
    ckt
    -0.15
    icias
    -0.15
     overcrow
    -0.15
    eros
    -0.14
    isode
    -0.14
    POSITIVE LOGITS
     course
    0.27
     objections
    0.26
     objection
    0.23
     threshold
    0.22
    top
    0.21
     counter
    0.21
     weekend
    0.21
     hurdle
    0.20
     shoulder
    0.20
     Fence
    0.20
    Act Density 0.047%

    No Known Activations