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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize complexity or depth beyond surface-level interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nanto
    -0.87
    bilt
    -0.78
    ãģ®ç
    -0.72
    âĹ¼
    -0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.71
    taboola
    -0.71
    soType
    -0.70
    CLASSIFIED
    -0.70
    isoft
    -0.67
     Accessed
    -0.67
    POSITIVE LOGITS
     mere
    0.88
     simply
    0.88
     merely
    0.86
     superficial
    0.83
     simple
    0.82
     oneself
    0.75
     caring
    0.74
     aesthetics
    0.72
     cosmetic
    0.72
     mundane
    0.72
    Act Density 0.121%

    No Known Activations