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

    Neuronpedia

    INDEX
    Explanations

    words related to growth or development

    oai_token-act-pair · gpt-3.5-turbo

    words and variations related to "doom" or "doomed" situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.69
    xx
    -0.68
    ilar
    -0.68
     Bezos
    -0.66
     =====
    -0.64
    uh
    -0.64
    ryu
    -0.63
    rik
    -0.62
     subp
    -0.61
     Comics
    -0.61
    POSITIVE LOGITS
    abouts
    0.73
    selves
    0.69
    DonaldTrump
    0.66
    glers
    0.66
    warm
    0.66
    stanbul
    0.65
     decay
    0.65
    nces
    0.64
    ORN
    0.64
    angering
    0.63
    Act Density 0.069%

    No Known Activations