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

    Neuronpedia

    INDEX
    Explanations

    words related to seduction and alluring qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Méd
    -0.16
    EMPLARY
    -0.15
    ádu
    -0.15
    ogui
    -0.15
    ilder
    -0.15
     Punch
    -0.14
    .refs
    -0.14
    elda
    -0.14
    illard
    -0.14
    ÑİÑĢ
    -0.14
    POSITIVE LOGITS
    uctive
    0.37
    uced
    0.33
    uction
    0.32
    iments
    0.30
    uct
    0.28
    ition
    0.26
    atives
    0.26
    ucer
    0.26
    ucing
    0.26
    uce
    0.25
    Act Density 0.005%

    No Known Activations