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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and indicators used in formal or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cowan
    -0.98
     Bader
    -0.98
     Carlin
    -0.95
    enchymal
    -0.90
    ogeneous
    -0.85
     restTemplate
    -0.85
    🔥🔥
    -0.81
     Wis
    -0.79
    modb
    -0.79
     Sis
    -0.79
    POSITIVE LOGITS
    ing
    2.79
    ING
    2.02
    ة
    1.07
    ingh
    1.00
    ingi
    0.98
    ingan
    0.90
    ingat
    0.87
    izing
    0.84
    ging
    0.83
    ating
    0.83
    Act Density 1.184%

    No Known Activations