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

    Neuronpedia

    INDEX
    Explanations

    phrases related to apprenticeships and companionship

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or collective entities involved in work or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scotia
    -0.79
     QC
    -0.72
    tto
    -0.71
     SER
    -0.70
     Newton
    -0.69
    tt
    -0.67
     Ok
    -0.66
     Ray
    -0.65
     Bern
    -0.64
     Situation
    -0.63
    POSITIVE LOGITS
    hip
    2.07
    hips
    1.60
    ervatives
    1.10
    uggest
    1.07
    andowski
    1.04
    atility
    1.04
    atile
    1.04
    ervative
    1.03
    terness
    1.00
    ateurs
    0.99
    Act Density 0.024%

    No Known Activations