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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases and structures in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubar
    -0.18
    uitka
    -0.16
    ıb
    -0.16
     èĹ
    -0.15
    lse
    -0.14
    λÏī
    -0.14
    foon
    -0.14
    StringBuilder
    -0.14
    ÃŃ
    -0.14
    slow
    -0.14
    POSITIVE LOGITS
     Tort
    0.18
    nat
    0.16
    ento
    0.15
     circumcision
    0.15
     Clip
    0.14
     Hern
    0.14
    rek
    0.14
     Lancaster
    0.14
     ups
    0.14
     -
    0.14
    Act Density 0.427%

    No Known Activations