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

    Neuronpedia

    INDEX
    Explanations

    concepts related to systemic structures and their implications within society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     would
    -0.19
     may
    -0.19
     was
    -0.18
     cannot
    -0.17
     is
    -0.17
    avra
    -0.16
     must
    -0.16
    lerdi
    -0.16
     should
    -0.16
    ozilla
    -0.16
    POSITIVE LOGITS
     ever
    0.31
     be
    0.30
     EVER
    0.21
     Ever
    0.21
     been
    0.21
     necessarily
    0.19
    Ever
    0.18
     Really
    0.17
    ever
    0.17
     REALLY
    0.16
    Act Density 0.108%

    No Known Activations