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

    Neuronpedia

    INDEX
    Explanations

    specific nouns or terms related to authority and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gap
    -0.17
     Gap
    -0.16
    afil
    -0.15
    nev
    -0.15
     gap
    -0.15
    resse
    -0.15
    nick
    -0.15
    aload
    -0.14
    .operations
    -0.14
    ickle
    -0.14
    POSITIVE LOGITS
     hor
    0.21
    LETE
    0.16
     fault
    0.16
    749
    0.15
    acher
    0.15
     Brotherhood
    0.15
     Pra
    0.14
    959
    0.14
    orning
    0.14
    onnement
    0.14
    Act Density 0.098%

    No Known Activations