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

    Neuronpedia

    INDEX
    Explanations

    phrases related to control and dominance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucky
    -0.15
     thần
    -0.15
    wick
    -0.15
    sey
    -0.15
    sid
    -0.15
     Fav
    -0.14
    uels
    -0.14
    HDR
    -0.14
    hud
    -0.14
    кав
    -0.14
    POSITIVE LOGITS
     control
    0.20
    /control
    0.20
    (control
    0.17
    control
    0.17
     minds
    0.17
    egra
    0.16
     proceedings
    0.16
     destiny
    0.16
    ehir
    0.16
     destin
    0.15
    Act Density 0.071%

    No Known Activations