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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to agreement and comparison of experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    agreement with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zas
    -0.42
     autorytatywna
    -0.39
     electrons
    -0.38
     jadi
    -0.36
    ActionCreators
    -0.35
     Lein
    -0.34
     asas
    -0.34
     Hamb
    -0.34
     allAfrica
    -0.33
     barn
    -0.33
    POSITIVE LOGITS
    EnumMember
    0.59
    GOTREF
    0.52
    toMatchSnapshot
    0.49
     <>",
    0.48
     løs
    0.47
    CodedInputStream
    0.46
    løs
    0.46
     accuracy
    0.45
    GeoNames
    0.44
     möge
    0.44
    Act Density 0.103%

    No Known Activations