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

    Neuronpedia

    INDEX
    Explanations

    phrases related to popular culture references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vangst
    -0.16
    etimes
    -0.15
     ilma
    -0.15
     Suites
    -0.15
    irable
    -0.14
    uesta
    -0.14
     surrogate
    -0.14
    è£ı
    -0.14
    engers
    -0.14
    erts
    -0.14
    POSITIVE LOGITS
    ÄĻ
    0.17
    iec
    0.16
    ÅĽ
    0.16
    ie
    0.16
    bie
    0.16
    adow
    0.16
    .rpm
    0.15
    oc
    0.15
    ier
    0.15
    bow
    0.15
    Act Density 0.083%

    No Known Activations