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

    Neuronpedia

    INDEX
    Explanations

    references to halls of fame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gel
    -0.16
    elman
    -0.15
    öl
    -0.15
    INC
    -0.15
    nt
    -0.14
    geh
    -0.14
    -feed
    -0.14
    ington
    -0.14
    ocrat
    -0.14
    upil
    -0.14
    POSITIVE LOGITS
     Fame
    0.39
     fame
    0.33
     fam
    0.21
     shame
    0.19
     indu
    0.18
     induction
    0.18
     Fam
    0.18
     Shame
    0.17
    duct
    0.16
    legg
    0.16
    Act Density 0.006%

    No Known Activations