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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the action of lifting or elevating objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Проци
    -0.96
     Pyle
    -0.93
    extAlignment
    -0.90
     Infórmanos
    -0.90
     profondeur
    -0.85
    seamnă
    -0.83
    ETHING
    -0.83
     SIAM
    -0.81
     utafitiHapana
    -0.81
    contentValues
    -0.80
    POSITIVE LOGITS
     lift
    1.63
     LIFT
    1.58
     lifted
    1.56
     lifts
    1.55
     Lift
    1.55
     lifting
    1.53
    Lift
    1.46
    lift
    1.34
     Lifting
    1.28
    lifted
    1.25
    Act Density 0.065%

    No Known Activations