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

    Neuronpedia

    INDEX
    Explanations

    forms of "be" indicating a state of existence

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating identity or roles

    np_token-act-pair-logits · gpt-4o-mini

    being

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.83
     cherchés
    -0.82
    ConstraintMaker
    -0.78
    ########.
    -0.77
    BagConstraints
    -0.74
    #+#
    -0.73
     виправивши
    -0.73
    expandindo
    -0.73
     Мексичка
    -0.71
     kasarigan
    -0.71
    POSITIVE LOGITS
     part
    0.57
     a
    0.53
     sisi
    0.48
    /*
    0.47
     in
    0.46
     surrounded
    0.45
     responsive
    0.44
     with
    0.44
    awtextra
    0.43
     effective
    0.42
    Act Density 4.694%

    No Known Activations