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

    Neuronpedia

    INDEX
    Explanations

    noun phrases with a demonstrative pronoun as a determiner

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     do
    -2.97
     Do
    -2.58
    Do
    -2.53
    do
    -2.50
     DO
    -2.08
    DO
    -1.76
     does
    -1.40
    does
    -1.36
     did
    -1.36
     don
    -1.31
    POSITIVE LOGITS
    enterOuterAlt
    0.79
    Hochspringen
    0.62
    umina
    0.58
     ivelany
    0.55
    Démographie
    0.53
     XMLHttpRequest
    0.52
    Portail
    0.51
    Chham
    0.50
     ComVisible
    0.50
    Примечания
    0.50
    Act Density 11.521%

    No Known Activations