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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of something being new or updated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Assisi
    -0.80
     saites
    -0.76
     acorns
    -0.75
     témo
    -0.74
    rophoresis
    -0.74
    ніципалі
    -0.73
    iconque
    -0.73
     ILogger
    -0.72
    präch
    -0.72
     SDI
    -0.71
    POSITIVE LOGITS
     new
    2.11
    new
    1.77
     New
    1.66
     NEW
    1.60
    新
    1.55
    New
    1.55
     nueva
    1.47
     nieuwe
    1.44
    新的
    1.43
    NEW
    1.43
    Act Density 0.122%

    No Known Activations