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

    Neuronpedia

    INDEX
    Explanations

    words related to specific significant body parts or actions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases associated with body parts and informal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occupancy
    -0.61
     confidentiality
    -0.60
    ele
    -0.59
    eur
    -0.58
     patronage
    -0.57
     arche
    -0.57
     referen
    -0.56
     Surveillance
    -0.56
    OSP
    -0.56
    araoh
    -0.55
    POSITIVE LOGITS
    mith
    1.27
    pring
    1.18
    heet
    1.16
    ayers
    1.09
    ome
    1.08
    ucker
    1.07
    dropping
    1.06
    leeve
    1.05
    poons
    1.05
    hift
    1.04
    Act Density 0.181%

    No Known Activations