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

    Neuronpedia

    INDEX
    Explanations

    references to responsibilities and interpersonal relations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -1.01
     kasarigan
    -0.76
    HideFlags
    -0.73
    ########.
    -0.71
     سكانية
    -0.69
     Taktlose
    -0.67
     Signalez
    -0.66
    
    -0.63
    Билгалдахарш
    -0.62
    RegressionTest
    -0.60
    POSITIVE LOGITS
     others
    2.26
     Others
    1.97
    others
    1.94
    Others
    1.89
     OTHERS
    1.73
     دیگران
    1.32
    别人
    1.22
     other
    1.21
     someone
    1.18
    他人
    1.13
    Act Density 0.285%

    No Known Activations