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

    Neuronpedia

    INDEX
    Explanations

    words related to admiration and respect

    oai_token-act-pair · gpt-3.5-turbo

    words related to admiration and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skelet
    -0.72
     Dunk
    -0.68
    TPS
    -0.65
    ters
    -0.65
     entrepreneurship
    -0.63
     kil
    -0.58
     automation
    -0.57
     coupled
    -0.57
     Redmond
    -0.56
    packs
    -0.55
    POSITIVE LOGITS
    iring
    1.46
    ittance
    1.23
    iral
    1.14
    ires
    1.14
    iries
    1.13
    iration
    1.09
    irable
    1.05
    isite
    1.05
    ired
    1.03
    reciation
    1.02
    Act Density 0.059%

    No Known Activations