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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal structures and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transitioning
    -0.19
     mash
    -0.18
     behaviors
    -0.18
     backstory
    -0.16
     referenced
    -0.16
    arbonate
    -0.15
     mashed
    -0.15
    visor
    -0.15
     parses
    -0.15
    <_
    -0.15
    POSITIVE LOGITS
    pole
    0.19
     pole
    0.18
     Olymp
    0.15
     consect
    0.15
     spokes
    0.15
     poc
    0.15
     judgement
    0.15
     massively
    0.15
     altogether
    0.15
     drastically
    0.15
    Act Density 0.095%

    No Known Activations