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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal experiences and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RuleContext
    -0.55
    SourceChecksum
    -0.53
    뀔
    -0.49
    loride
    -0.49
    ліза
    -0.47
    рп
    -0.47
    ittä
    -0.46
    çalves
    -0.46
     mahdol
    -0.46
    Diweddarwch
    -0.46
    POSITIVE LOGITS
     really
    3.22
    really
    2.94
    Really
    2.70
     Really
    2.67
     realmente
    2.10
     REALLY
    2.07
     realy
    1.93
     vraiment
    1.83
     actually
    1.81
     wirklich
    1.79
    Act Density 0.364%

    No Known Activations