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

    Neuronpedia

    INDEX
    Explanations

    references to social identity and the impact of societal expectations

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

    Following comparatives ("as", "like", "same")

    np_acts-logits-general · gemini-2.0-flash

    comparison of unlike things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encounter
    -0.40
     bleek
    -0.33
     fee
    -0.33
     resulting
    -0.31
     otherwise
    -0.30
     encounters
    -0.30
     soundly
    -0.30
     fees
    -0.30
     narrow
    -0.30
     giro
    -0.29
    POSITIVE LOGITS
    amerikanischer
    0.63
     EconPapers
    0.57
    glLoad
    0.52
    Imit
    0.52
     TextAppearance
    0.52
    Únete
    0.52
     iconLine
    0.51
    ंदीखरीदारी
    0.51
    GMENT
    0.50
     thoſe
    0.50
    Act Density 0.380%

    No Known Activations