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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditionality or stipulations

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

    given clause starter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rujuakan
    -0.51
    quiao
    -0.44
    anyeol
    -0.40
    mangle
    -0.38
    USC
    -0.38
    ngrx
    -0.38
     actionPerformed
    -0.37
     beaver
    -0.36
    requireNonNull
    -0.36
     Renn
    -0.36
    POSITIVE LOGITS
    Given
    2.22
     Given
    2.19
    given
    2.14
     GIVEN
    1.91
     given
    1.88
     dado
    1.10
     donné
    1.08
    Dado
    1.07
     Dado
    1.07
     dadas
    1.02
    Act Density 0.005%

    No Known Activations