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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Venus" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lins
    -0.82
     Mellon
    -0.81
    REC
    -0.80
    alach
    -0.79
    resso
    -0.79
    ointed
    -0.77
    intosh
    -0.74
    mie
    -0.73
    oley
    -0.72
    doms
    -0.71
    POSITIVE LOGITS
     Venus
    0.90
     Vega
    0.79
    uous
    0.78
     eclipse
    0.78
    uve
    0.78
     goddess
    0.77
    mouth
    0.77
    ectomy
    0.75
     Gemini
    0.72
    antes
    0.70
    Act Density 0.012%

    No Known Activations