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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or examples

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "such" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antage
    -0.71
    vell
    -0.61
    orem
    -0.60
    ille
    -0.59
     Welcome
    -0.57
    VR
    -0.57
    essor
    -0.57
    oil
    -0.56
    emi
    -0.56
    oS
    -0.56
    POSITIVE LOGITS
    ties
    0.92
    ones
    0.76
    inyl
    0.69
    ities
    0.68
     disagreements
    0.63
    minded
    0.61
     arrang
    0.61
    etheless
    0.61
    amount
    0.60
    Flag
    0.59
    Act Density 0.037%

    No Known Activations