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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation or summary statements

    oai_token-act-pair · gpt-3.5-turbo

    statements of opinion and summaries of overall impressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.74
    ufact
    -0.67
    rack
    -0.66
    numbered
    -0.66
    legged
    -0.65
    rils
    -0.65
     previously
    -0.64
    osponsors
    -0.63
     predecessors
    -0.63
    bor
    -0.62
    POSITIVE LOGITS
     concludes
    0.74
    iem
    0.72
     boils
    0.69
    merce
    0.67
    ibaba
    0.66
     resil
    0.66
     takeaway
    0.64
     usefulness
    0.63
    rust
    0.63
     warr
    0.63
    Act Density 0.206%

    No Known Activations