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

    Neuronpedia

    INDEX
    Explanations

    comparisons or similes

    oai_token-act-pair · gpt-3.5-turbo

    words associated with comparisons or similes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.85
     Nou
    -0.79
    cules
    -0.71
    ACA
    -0.69
    trl
    -0.67
    INA
    -0.66
     Mass
    -0.64
     residency
    -0.64
     Schools
    -0.62
     Frie
    -0.62
    POSITIVE LOGITS
    lihood
    1.60
     lik
    0.97
    lik
    0.96
    ability
    0.87
    liness
    0.85
    ened
    0.80
    iour
    0.78
    ening
    0.77
    eness
    0.76
     likeness
    0.76
    Act Density 0.010%

    No Known Activations