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

    Neuronpedia

    INDEX
    Explanations

    references to technical systems and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.67
    nai
    -0.64
    "]=>
    -0.62
    licts
    -0.62
    emale
    -0.61
    bernatorial
    -0.60
    bledon
    -0.56
    emetery
    -0.55
    "><
    -0.55
    blems
    -0.54
    POSITIVE LOGITS
     techniques
    0.59
     ingenuity
    0.59
     imagination
    0.57
     infusion
    0.57
     technique
    0.56
     apparatus
    0.55
     ingenious
    0.54
     prism
    0.54
     annotations
    0.53
     tools
    0.52
    Act Density 0.552%

    No Known Activations