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

    Neuronpedia

    INDEX
    Explanations

    words that indicate equivalence or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Abp
    -0.46
    BeforeClass
    -0.45
     kasarigan
    -0.44
    склад
    -0.43
     chung
    -0.43
    rån
    -0.43
    tamin
    -0.42
     huyền
    -0.40
    ritage
    -0.40
     Cri
    -0.40
    POSITIVE LOGITS
     equivalent
    2.53
    equivalent
    2.17
     Equivalent
    2.04
     equivalents
    2.03
     equivalente
    2.00
     equival
    1.98
    équi
    1.94
     équi
    1.93
     equivalence
    1.85
    Equivalent
    1.82
    Act Density 0.448%

    No Known Activations