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

    Neuronpedia

    INDEX
    Explanations

    personal feelings or desires expressed in the first person

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal desires or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jan
    -0.68
     darts
    -0.63
     sqor
    -0.62
    theless
    -0.61
     Roses
    -0.59
     heels
    -0.59
    Hero
    -0.59
     anytime
    -0.58
    jas
    -0.58
     Classes
    -0.58
    POSITIVE LOGITS
    oyer
    0.77
    idding
    0.67
    otos
    0.67
    erous
    0.64
    ynski
    0.64
     equation
    0.64
     guiActiveUnfocused
    0.61
    xual
    0.61
     Older
    0.59
    selage
    0.58
    Act Density 0.231%

    No Known Activations