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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "are" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    žin
    -0.64
    Sims
    -0.60
    мышлен
    -0.60
    
    -0.59
    icity
    -0.58
    SIN
    -0.58
    ilit
    -0.57
     itself
    -0.57
     neuem
    -0.56
    firstChild
    -0.56
    POSITIVE LOGITS
     themselves
    1.22
     yourselves
    1.20
     are
    1.16
    themselves
    1.11
     were
    1.03
    wolves
    1.02
     ARE
    1.01
     voltak
    0.97
     WERE
    0.96
    were
    0.94
    Act Density 0.572%

    No Known Activations