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

    Neuronpedia

    INDEX
    Explanations

    actions related to manipulation and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ніципалі
    -0.46
    UnusedPrivate
    -0.43
    astify
    -0.41
    SPJ
    -0.40
     stopped
    -0.40
    Bia
    -0.40
    ncy
    -0.40
     referrerpolicy
    -0.40
    Чыганаклар
    -0.40
     Reti
    -0.40
    POSITIVE LOGITS
     manipulations
    1.14
     manipulation
    1.13
    manip
    1.07
     manipulating
    1.06
    Manipulation
    1.05
     manipulate
    1.05
     manipulated
    1.00
     manip
    1.00
     Manipulation
    0.99
     manipula
    0.94
    Act Density 0.941%

    No Known Activations