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

    Neuronpedia

    INDEX
    Explanations

    references to elements of human existence and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arten
    -0.18
    oenix
    -0.18
    exampleInputEmail
    -0.16
    AREA
    -0.15
    alace
    -0.15
    stery
    -0.15
    ripper
    -0.14
    oldemort
    -0.14
    idon
    -0.14
    autiful
    -0.14
    POSITIVE LOGITS
     seu
    0.21
     nosso
    0.17
     próp
    0.16
     veto
    0.16
     último
    0.16
     mesmo
    0.15
     segundo
    0.15
    λά
    0.15
     antagon
    0.15
    annis
    0.15
    Act Density 0.013%

    No Known Activations