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

    Neuronpedia

    INDEX
    Explanations

    information related to research and technical details

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to systems and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Farm
    -0.77
    Gate
    -0.74
    zai
    -0.74
    Virgin
    -0.74
    Lago
    -0.72
    aters
    -0.70
    Bee
    -0.70
    Born
    -0.69
    WB
    -0.69
    acho
    -0.68
    POSITIVE LOGITS
     discusses
    1.18
     outlines
    1.08
     concludes
    1.06
     illustrating
    1.06
     explaining
    1.05
     discuss
    1.05
     explanations
    1.04
     explain
    1.03
     summarize
    1.02
     summarizes
    1.01
    Act Density 0.439%

    No Known Activations