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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "in" along with variations of spatial and directional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    生
    -0.51
     (;;
    -0.50
     fuori
    -0.48
    setProduct
    -0.48
    尖
    -0.45
     offen
    -0.45
    Inferno
    -0.42
     Registered
    -0.42
    ěst
    -0.41
    itsch
    -0.41
    POSITIVE LOGITS
     moves
    1.66
     move
    1.61
     Moves
    1.56
     MOVE
    1.55
     Move
    1.54
    MOVE
    1.54
     movement
    1.50
     moving
    1.50
    move
    1.49
    moves
    1.48
    Act Density 0.159%

    No Known Activations