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

    Neuronpedia

    INDEX
    Explanations

    terms related to structural damage or vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mathias
    -0.75
    yoshi
    -0.74
     Mathias
    -0.73
    onomie
    -0.72
    ={{
    -0.70
    Amelia
    -0.69
    mbols
    -0.69
    ψη
    -0.69
    axel
    -0.68
     Kowal
    -0.68
    POSITIVE LOGITS
     crack
    2.02
     cracks
    1.97
    crack
    1.77
     cracking
    1.72
     Cracks
    1.72
     cracked
    1.71
     Crack
    1.70
     CRACK
    1.68
    Crack
    1.58
     Cracking
    1.56
    Act Density 0.089%

    No Known Activations