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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to planning, actions, and consequences

    oai_token-act-pair · gemini-2.0-flash

    Variations of "move"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagMode
    -0.84
    
    -0.65
     EconPapers
    -0.62
    ISupport
    -0.60
    IsContent
    -0.57
    saraba
    -0.55
    protoimpl
    -0.54
     betweenstory
    -0.54
    ]");
    -0.51
    IsMutable
    -0.51
    POSITIVE LOGITS
     moves
    1.48
     move
    1.43
    moves
    1.30
     Moves
    1.30
    move
    1.28
     Move
    1.22
     movement
    1.20
    Move
    1.19
     movements
    1.18
     movimientos
    1.17
    Act Density 1.203%

    No Known Activations