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

    Neuronpedia

    INDEX
    Explanations

    verbs and adjectives related to generalizing, applying, and demonstrating concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to application and generalization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.77
    unts
    -0.76
    etsk
    -0.70
     Bomber
    -0.65
    asus
    -0.64
    fur
    -0.63
     Queen
    -0.62
     Duchess
    -0.61
    phies
    -0.59
     nap
    -0.59
    POSITIVE LOGITS
    soType
    0.79
    arity
    0.79
    sheets
    0.79
     applic
    0.74
     applications
    0.74
    itarian
    0.73
     Functions
    0.71
     geographically
    0.70
    velength
    0.70
     Spectrum
    0.70
    Act Density 0.181%

    No Known Activations