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

    Neuronpedia

    INDEX
    Explanations

    indicators of educational resources and discussions about historical events, particularly regarding race and stereotypes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ideia
    -0.55
    orance
    -0.54
     zeitung
    -0.54
    ytale
    -0.54
     enfans
    -0.54
    henswürdigkeiten
    -0.53
     Zustimmung
    -0.52
     xrange
    -0.52
    ILayout
    -0.52
    ARANCE
    -0.51
    POSITIVE LOGITS
     •
    2.08
    •
    1.98
    .•
    1.67
    ••
    1.66
    )•
    1.61
    •••
    1.46
    ••••
    1.41
     ••
    1.38
    €¢
    1.30
    ~•
    1.23
    Act Density 0.148%

    No Known Activations