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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific technical terms

    oai_token-act-pair · gpt-3.5-turbo

    specific types of roles or positions tied to authority or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interchange
    -0.88
     vested
    -0.71
     metaphor
    -0.66
     correspondent
    -0.65
     uphill
    -0.64
     refrain
    -0.64
     infringing
    -0.63
     equilibrium
    -0.62
     respons
    -0.62
     dimin
    -0.62
    POSITIVE LOGITS
    ater
    1.00
    aris
    0.97
    ī
    0.94
    xes
    0.94
    ctions
    0.94
    ques
    0.94
    aker
    0.91
    ases
    0.91
    OME
    0.90
    ante
    0.90
    Act Density 0.729%

    No Known Activations