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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-identification and self-assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    self-reported or self-identified information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.57
    LEGGI
    -0.56
     الرياضيه
    -0.54
    brainly
    -0.54
    onomía
    -0.53
     للمعارف
    -0.51
     snippetHide
    -0.49
     plufieurs
    -0.48
    DockStyle
    -0.48
    KommentareTeilen
    -0.47
    POSITIVE LOGITS
    claimed
    0.62
     self
    0.62
     proud
    0.54
    self
    0.54
     confessed
    0.51
     professed
    0.50
     proclaimed
    0.50
     Zwick
    0.49
     former
    0.48
     Self
    0.46
    Act Density 0.010%

    No Known Activations