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

    Neuronpedia

    INDEX
    Explanations

    phrases where the concept of "sameness" or similarity is emphasized

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express similarity or equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WI
    -0.73
    rollers
    -0.72
    Ķ
    -0.71
    rection
    -0.70
    orts
    -0.69
    ronics
    -0.69
    arest
    -0.68
    rosso
    -0.68
    rique
    -0.67
    xtap
    -0.67
    POSITIVE LOGITS
     thing
    1.29
     way
    1.00
     exact
    0.89
     amount
    0.88
     size
    0.86
     kind
    0.85
     extent
    0.81
     anymore
    0.81
     regardless
    0.81
     sort
    0.80
    Act Density 0.045%

    No Known Activations