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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating prior ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     still
    -0.29
    still
    -0.29
     ancora
    -0.28
     ainda
    -0.28
     Still
    -0.28
    Still
    -0.25
     STILL
    -0.25
    å°ļ
    -0.24
     aún
    -0.24
     ìķĦì§ģ
    -0.23
    POSITIVE LOGITS
    -existing
    0.23
    chaft
    0.19
    -established
    0.19
     established
    0.18
     begun
    0.17
     plenty
    0.16
    existing
    0.16
     familiar
    0.15
    -fashioned
    0.15
     existed
    0.15
    Act Density 0.055%

    No Known Activations