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

    Neuronpedia

    INDEX
    Explanations

    phrases related to access to various resources and services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to access and availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernand
    -0.78
    NR
    -0.78
    boxing
    -0.75
    ieu
    -0.69
    sect
    -0.67
    NL
    -0.65
    hetical
    -0.65
    oval
    -0.64
    rust
    -0.63
    union
    -0.63
    POSITIVE LOGITS
     resources
    0.73
     Pandora
    0.72
    tnc
    0.70
     Antiqu
    0.68
    agnetic
    0.65
     restrooms
    0.65
    site
    0.64
    hold
    0.63
     information
    0.62
     Territories
    0.62
    Act Density 0.057%

    No Known Activations