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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases that indicate movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    moves forward and between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elseif
    -0.49
    出版年
    -0.43
    点此举报
    -0.40
     elseif
    -0.38
    elif
    -0.37
    unknownFields
    -0.36
    сыз
    -0.35
    expandindo
    -0.34
     melu
    -0.33
     antig
    -0.33
    POSITIVE LOGITS
     Mover
    0.94
     move
    0.92
     Move
    0.90
     movers
    0.89
     moves
    0.89
     MOVE
    0.88
     Moves
    0.88
     mover
    0.87
    moves
    0.86
     Movers
    0.85
    Act Density 0.017%

    No Known Activations