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

    Neuronpedia

    INDEX
    Explanations

    words related to specific terms or names, particularly those ending in 'ite'

    oai_token-act-pair · gpt-3.5-turbo

    words related to types of minerals or geological features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ood
    -0.96
    aii
    -0.91
    recated
    -0.88
    INGTON
    -0.85
    acies
    -0.81
    enegger
    -0.79
     "$:/
    -0.78
    ington
    -0.78
    acy
    -0.78
    kefeller
    -0.77
    POSITIVE LOGITS
    chnology
    0.92
    lli
    0.88
    geist
    0.73
    eer
    0.72
    OPLE
    0.68
     Scotia
    0.67
    pec
    0.66
    venants
    0.64
    eers
    0.63
    fish
    0.62
    Act Density 0.033%

    No Known Activations