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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "even" along with its context, focusing on exceptions or qualifications in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تانيه
    -0.52
    ::::::::
    -0.50
    ⓧ
    -0.47
    rsiniz
    -0.47
     escul
    -0.44
    ništvo
    -0.44
     blues
    -0.43
     decis
    -0.42
    PhysRevLett
    -0.42
     cæ
    -0.41
    POSITIVE LOGITS
     siquiera
    0.96
     even
    0.89
    ंदीखरीदारी
    0.80
     remotely
    0.77
     ogóle
    0.75
    even
    0.73
    providedIn
    0.72
     barely
    0.71
    AccessorTable
    0.70
     bother
    0.70
    Act Density 0.192%

    No Known Activations