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
    -0.69
    ars
    -0.66
    NAT
    -0.65
    inx
    -0.64
    gran
    -0.63
     wound
    -0.61
     DOT
    -0.61
     Rebellion
    -0.59
    antis
    -0.59
    ARS
    -0.58
    POSITIVE LOGITS
     leisure
    1.15
    isure
    1.11
     trave
    0.89
     ende
    0.83
    bnb
    0.83
    shire
    0.82
    emouth
    0.82
    lihood
    0.81
     seiz
    0.81
     intrins
    0.77
    Act Density 0.008%

    No Known Activations