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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusive access or membership

    oai_token-act-pair · gpt-3.5-turbo

    references to exclusivity and special access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olesterol
    -0.81
    aper
    -0.78
    apers
    -0.76
    annis
    -0.76
    ;;;;;;;;;;;;
    -0.71
    immers
    -0.70
    ohan
    -0.69
    abases
    -0.69
    phrine
    -0.68
    aptic
    -0.68
    POSITIVE LOGITS
     exclusively
    0.97
     exclusive
    0.94
     exclus
    0.93
     privileges
    0.92
    exclusive
    0.81
     warr
    0.75
     rights
    0.75
    bidden
    0.70
    ities
    0.70
     forbidden
    0.70
    Act Density 0.008%

    No Known Activations