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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DrawerToggle
    -0.57
     Chel
    -0.56
     Dall
    -0.56
     vengan
    -0.56
    Liefer
    -0.55
     floats
    -0.54
     lauk
    -0.51
     Entrega
    -0.51
     AppColors
    -0.51
     picker
    -0.50
    POSITIVE LOGITS
    ToAction
    1.14
     actions
    1.10
    actions
    1.02
     action
    0.99
     Actions
    0.99
     steps
    0.98
    Actions
    0.96
     actie
    0.93
     ACTION
    0.88
     Action
    0.87
    Act Density 0.205%

    No Known Activations