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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical entryways or access points

    oai_token-act-pair · gpt-3.5-turbo

    mentions of entrances or access points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ient
    -0.66
    Model
    -0.66
    Mess
    -0.66
    ients
    -0.62
    uzz
    -0.61
    iency
    -0.60
    arrell
    -0.60
     Alloy
    -0.59
     Projects
    -0.59
    netflix
    -0.58
    POSITIVE LOGITS
     entrance
    3.77
     entrances
    2.88
     entry
    1.89
     exit
    1.88
     admission
    1.73
     doorway
    1.66
     Entry
    1.37
     exits
    1.36
     gates
    1.36
     Exit
    1.35
    Act Density 0.008%

    No Known Activations