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

    Neuronpedia

    INDEX
    Explanations

    references to increased risk of negative health outcomes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to risk factors associated with health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elf
    -0.82
    issance
    -0.77
    ilver
    -0.76
     Remastered
    -0.76
     Seasons
    -0.71
    æ©Ł
    -0.69
    poons
    -0.67
    VIDEO
    -0.66
    TERN
    -0.66
    zeb
    -0.64
    POSITIVE LOGITS
     factors
    0.90
     factor
    0.88
     tolerance
    0.76
    taking
    0.75
     reduction
    0.75
     horm
    0.75
    iest
    0.74
     allele
    0.74
     aversion
    0.74
     slope
    0.74
    Act Density 0.019%

    No Known Activations