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

    Neuronpedia

    INDEX
    Explanations

    words related to the release or emission of substances or materials

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.73
    tarians
    -0.71
    lihood
    -0.70
    éĸ
    -0.70
    relation
    -0.68
    istani
    -0.68
    assian
    -0.68
    ggles
    -0.67
    gamer
    -0.66
    ĻĤ
    -0.66
    POSITIVE LOGITS
     forth
    1.08
     havoc
    0.98
     toxins
    0.90
     onto
    0.88
     bursts
    0.86
     fumes
    0.86
     gallons
    0.86
     projectiles
    0.84
     outward
    0.83
     uncontroll
    0.83
    Act Density 0.107%

    No Known Activations