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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "disclosure" and its variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    jface
    -0.76
     Britann
    -0.72
    wein
    -0.72
     BRIT
    -0.72
    interopRequire
    -0.70
     Nutt
    -0.69
     jScrollPane
    -0.69
    ResumeLayout
    -0.68
    !*\
    -0.66
    πί
    -0.66
    POSITIVE LOGITS
    disclosure
    0.96
     disclosure
    0.88
     disclose
    0.88
     Disclosure
    0.88
    CLOSURE
    0.84
     disclosed
    0.78
    Disclosure
    0.73
     discloses
    0.72
     disclosing
    0.71
    closures
    0.68
    Act Density 0.008%

    No Known Activations