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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence metrics and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.34
    ']){
    -0.33
     dars
    -0.33
    /**
    -0.33
    🦕
    -0.31
    🥩
    -0.31
     stejně
    -0.30
    꿔
    -0.30
    ]()
    -0.29
    })`
    -0.29
    POSITIVE LOGITS
    исленность
    0.68
     kasarigan
    0.57
    SourceChecksum
    0.57
    httphttps
    0.54
     Vikipedi
    0.54
     idéia
    0.52
    TAWA
    0.50
     CURIAM
    0.50
    GEBURTSDATUM
    0.50
    wußt
    0.50
    Act Density 0.063%

    No Known Activations