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

    Neuronpedia

    INDEX
    Explanations

    words related to medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to opulence and excess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.75
    ctory
    -0.69
    Philipp
    -0.65
     CoC
    -0.61
     psychiatrist
    -0.61
     Ahmad
    -0.61
     Consent
    -0.61
     Lia
    -0.60
    emb
    -0.60
    Ont
    -0.60
    POSITIVE LOGITS
    ulence
    3.49
    opian
    0.86
    rity
    0.85
    stration
    0.84
    esity
    0.84
     Seym
    0.82
    aughtered
    0.76
     probes
    0.75
     gadgets
    0.73
     snag
    0.72
    Act Density 0.025%

    No Known Activations