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

    Neuronpedia

    INDEX
    Explanations

    numerical or measurement details related to specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĹıèĩªæ²»
    -0.16
    ERRU
    -0.15
     Ramsey
    -0.15
    hrad
    -0.15
    ìĹ´
    -0.15
    raquo
    -0.15
    Mods
    -0.15
    ifest
    -0.15
    USTOM
    -0.14
    utow
    -0.14
    POSITIVE LOGITS
     LB
    0.24
     lb
    0.22
     caught
    0.22
     leg
    0.22
     wide
    0.20
     york
    0.20
    -leg
    0.20
     ump
    0.20
    LB
    0.19
     Caught
    0.19
    Act Density 0.007%

    No Known Activations