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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to be" in multiple tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.63
    giarism
    -0.55
     transfieras
    -0.51
    thodes
    -0.48
     Ад
    -0.47
    bür
    -0.46
     bezeichneter
    -0.45
    ModelAdmin
    -0.45
     folie
    -0.45
    []);
    -0.45
    POSITIVE LOGITS
     concerned
    1.13
     aware
    0.94
    concerned
    0.93
     worried
    0.91
     disappointed
    0.89
     dismayed
    0.88
     confident
    0.88
     pleased
    0.87
     displeased
    0.86
     optimistic
    0.85
    Act Density 0.360%

    No Known Activations