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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and conditions involving relationships and comparisons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     allotted
    -0.06
     arbitrarily
    -0.06
    WebKit
    -0.06
    ieri
    -0.06
    uncios
    -0.06
     concurrently
    -0.06
    344
    -0.06
     éĸ¢éĢ£
    -0.06
    629
    -0.06
    abolic
    -0.06
    POSITIVE LOGITS
     dán
    0.10
    /rem
    0.08
    ,but
    0.08
    ,and
    0.07
    /is
    0.07
    .Then
    0.07
     kinda
    0.07
     nackte
    0.07
     dün
    0.07
     kém
    0.07
    Act Density 0.001%

    No Known Activations