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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical health and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    discussions around categories and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eworks
    -0.87
    abase
    -0.80
    agents
    -0.75
    zone
    -0.75
    quer
    -0.74
    enth
    -0.72
     prosec
    -0.71
    third
    -0.71
     Secondly
    -0.70
    fourth
    -0.69
    POSITIVE LOGITS
     unmist
    0.99
     ominous
    0.93
     swast
    0.93
     bland
    0.92
     nudity
    0.89
     nausea
    0.87
     sadness
    0.84
     themes
    0.84
     catchy
    0.84
     flashy
    0.83
    Act Density 0.533%

    No Known Activations