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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressions of amazement or shock

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blackwell
    -0.69
     Galactic
    -0.66
     Holo
    -0.65
     Investors
    -0.65
    markets
    -0.65
    istant
    -0.64
     Scotia
    -0.64
    houses
    -0.63
    holders
    -0.61
    agents
    -0.61
    POSITIVE LOGITS
    bone
    1.37
    bones
    1.30
    doms
    0.97
    dropping
    0.96
    Bone
    0.92
    bons
    0.92
    line
    0.91
    keye
    0.87
    lines
    0.85
    bon
    0.83
    Act Density 0.024%

    No Known Activations