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

    Neuronpedia

    INDEX
    Explanations

    expressions of knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     åĶ
    -0.16
    shaw
    -0.15
    ="__
    -0.15
    ocker
    -0.15
    703
    -0.14
     herein
    -0.14
    γοÏģ
    -0.14
    ë¥
    -0.14
    dt
    -0.13
     neither
    -0.13
    POSITIVE LOGITS
     until
    0.23
     till
    0.21
    until
    0.19
     Until
    0.18
    til
    0.17
     existence
    0.17
     existed
    0.16
    ingly
    0.16
    Until
    0.16
     danger
    0.15
    Act Density 0.096%

    No Known Activations