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

    Neuronpedia

    INDEX
    Explanations

    terms related to critical thinking and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lifelong
    -0.15
    -existent
    -0.15
    anz
    -0.14
    /inet
    -0.14
    êu
    -0.14
    acier
    -0.14
    nika
    -0.14
    enia
    -0.14
    bah
    -0.13
    FromClass
    -0.13
    POSITIVE LOGITS
    ãĥªãĥ³ãĤ°
    0.15
    ánh
    0.15
    seg
    0.14
     probe
    0.14
     german
    0.14
    abbit
    0.14
     seg
    0.14
     tang
    0.13
    ding
    0.13
    OSH
    0.13
    Act Density 0.004%

    No Known Activations