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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    indow
    -0.07
     stan
    -0.07
     tip
    -0.07
     Tip
    -0.07
    Ñģклад
    -0.06
     Saud
    -0.06
    secutive
    -0.06
     legit
    -0.06
     tw
    -0.06
     seasonal
    -0.06
    POSITIVE LOGITS
     another
    0.10
    same
    0.10
     same
    0.10
    another
    0.10
    åIJĮ
    0.10
     ëĺIJ
    0.10
     again
    0.09
    Same
    0.09
     Same
    0.09
    Again
    0.09
    Act Density 0.141%

    No Known Activations