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

    Neuronpedia

    INDEX
    Explanations

    economic and political terms related to policies and strategies

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to dualities or contrasts, particularly in social or economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.74
    ©¶æ
    -0.68
    ople
    -0.68
    hari
    -0.66
    ortium
    -0.66
    started
    -0.66
     Oo
    -0.65
    ¯¯¯¯¯¯¯¯
    -0.65
     Suppose
    -0.64
    76561
    -0.63
    POSITIVE LOGITS
     broader
    1.06
     others
    1.04
     other
    0.99
     actual
    0.94
     downright
    0.94
     equally
    0.85
     nonetheless
    0.84
     deeper
    0.84
     wider
    0.84
     underlying
    0.83
    Act Density 0.776%

    No Known Activations