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

    Neuronpedia

    INDEX
    Explanations

    references to specific states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersh
    -0.16
    ird
    -0.16
    IRD
    -0.16
    akin
    -0.15
    uran
    -0.14
    ssp
    -0.14
    odos
    -0.14
    ause
    -0.14
    ulk
    -0.14
     spit
    -0.14
    POSITIVE LOGITS
     affairs
    0.58
     Affairs
    0.45
     affair
    0.42
     play
    0.31
     mind
    0.31
     flux
    0.30
     Flux
    0.27
    mind
    0.27
     emergency
    0.26
     Siege
    0.26
    Act Density 0.021%

    No Known Activations