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

    Neuronpedia

    INDEX
    Explanations

    terms indicating comparison or correspondence between entities or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wahr
    -0.38
    יף
    -0.37
     skład
    -0.36
    def
    -0.36
    fies
    -0.36
    éges
    -0.35
    ссора
    -0.35
     />);
    -0.34
    Terms
    -0.34
    kter
    -0.34
    POSITIVE LOGITS
    OGND
    0.90
    IntoConstraints
    0.90
     ligiloj
    0.78
     المعيارى
    0.78
    曖昧さ回避
    0.77
    0.76
     estekak
    0.75
     equivalent
    0.74
    harusnya
    0.73
     counterparts
    0.72
    Act Density 0.388%

    No Known Activations