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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant changes or requirements in societal or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ellers
    -0.35
    Kariera
    -0.33
     otherwise
    -0.33
    dyž
    -0.31
    <?
    -0.31
    Források
    -0.30
     egna
    -0.30
     Auss
    -0.29
     experiences
    -0.28
     виправивши
    -0.28
    POSITIVE LOGITS
     tendency
    0.88
     possibility
    0.85
     danger
    0.83
    possibility
    0.81
     reason
    0.79
     limit
    0.75
     temptation
    0.74
     caveat
    0.74
     difference
    0.73
     dearth
    0.72
    Act Density 0.438%

    No Known Activations