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

    Neuronpedia

    INDEX
    Explanations

    phrases related to empowerment, control, and autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OpenHelper
    -0.63
    richTextPanel
    -0.60
    WithMany
    -0.60
    ɵɵelementStart
    -0.58
    hartt
    -0.55
    umuz
    -0.54
    AndEndTag
    -0.54
     Condol
    -0.53
     vire
    -0.53
     animo
    -0.53
    POSITIVE LOGITS
     autonomy
    0.69
     control
    0.67
     zelf
    0.63
     Self
    0.62
     self
    0.61
     rights
    0.61
     sovereignty
    0.61
     dignité
    0.59
     Control
    0.59
     eigener
    0.58
    Act Density 0.321%

    No Known Activations