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

    Neuronpedia

    INDEX
    Explanations

    words related to seduction

    oai_token-act-pair · gpt-3.5-turbo

    words related to seduction and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.71
     Briggs
    -0.66
    BOOK
    -0.63
    boards
    -0.63
     Soda
    -0.62
    sticks
    -0.62
    head
    -0.62
    ãĥ£
    -0.62
    SHIP
    -0.61
    heads
    -0.60
    POSITIVE LOGITS
    uctive
    1.68
    entary
    1.63
    uction
    1.57
    ucing
    1.36
    uct
    1.36
    uce
    1.35
    iments
    1.34
    uctions
    1.33
    uced
    1.28
    uces
    1.28
    Act Density 0.030%

    No Known Activations