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

    Neuronpedia

    INDEX
    Explanations

    words related to relaxation and free time activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to leisure activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imposed
    -0.76
    ars
    -0.72
    nikov
    -0.72
    arov
    -0.69
    oded
    -0.69
    oted
    -0.68
    inx
    -0.68
    infect
    -0.66
    anyahu
    -0.65
    inki
    -0.64
    POSITIVE LOGITS
     pursuits
    1.01
    ly
    1.00
    isure
    0.98
     leisure
    0.85
    bnb
    0.75
     Suit
    0.70
     jour
    0.70
     endeav
    0.70
     lifestyles
    0.69
    shire
    0.68
    Act Density 0.026%

    No Known Activations