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

    Neuronpedia

    INDEX
    Explanations

    references to different hierarchical levels or rankings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sund
    -0.79
    lez
    -0.76
    pload
    -0.73
    Thunder
    -0.70
    Thor
    -0.70
    rower
    -0.69
    ELY
    -0.69
    ãĥ¡
    -0.68
    oute
    -0.68
    fect
    -0.67
    POSITIVE LOGITS
     crossings
    0.70
     certific
    0.68
    hips
    0.67
    chart
    0.67
    atics
    0.64
    icz
    0.63
     recognize
    0.62
    ear
    0.62
    enance
    0.60
    smanship
    0.60
    Act Density 0.020%

    No Known Activations